STRIDE ablation using one pooled reasoning embedding per eligible response. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is 64…
SAVRN Model Hub · Models by Task
Text Generation Models
338 open-weight text generation models in the SAVRN Model Hub, with Convergent Intelligence, Qwen and Kumar publishing the most.
338Models
136Publishers
466,176 to 753.3BParameter range
8Licenses
SAVRN's Take
Of the 338 models we catalog under text generation, 91 are indexed against live hourly GPU prices, and the parameter range runs from 466,176 to 753.3B. The largest, GLM-5.2-FP8 from Z.ai, carries a 1,048,576-token context and needs 1,808 GB at 16-bit, which is 8 MI325X at $16.00 an hour; at 4-bit it fits in 452 GB on 2 MI325X at $4.00 an hour, and that factor of four is our first lever. Most of what people pull sits below that: Qwen3-8B needs 19.7 GB at 16-bit, Qwen2.5-7B-Instruct 18.3 GB, each on one MI300X at $1.85 an hour.
Downloads show the demand. Qwen3-0.6B leads at 22,498,727 a month, then gpt2 at 15,439,333, Qwen3-8B at 12,988,756 and Unsloth AI's Qwen3-Coder-30B-A3B-Instruct-GGUF at 12,752,716. Six of the top eight are Qwen models or Qwen builds repackaged by Unsloth AI and NVIDIA. By count, Convergent Intelligence publishes the most at 52, ahead of Qwen at 42, Kumar at 14, Park at 12 and NVIDIA at 11.
On licensing, 164 models are Apache 2.0 and 41 are MIT, the clean end for commercial use. Another 51 state no license, 41 are marked other, 13 sit under Llama 3 terms and 5 under Llama 3.2, each needing a read first. Before we commit a card we check that the license is stated, that the 16-bit and 4-bit figures fit the hardware we own, that the context covers the job (40,960 tokens on Qwen3-8B, 32,768 on Qwen2.5-7B-Instruct, 2,048 on opt-125m), and that a parameter count is published, and only 223 of 338 do.
Most Downloaded
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| Qwen3-0.6B | Qwen | 752M | apache-2.0 | 22.5M | 1x MI300X, $1.85/hr |
| gpt2 | OpenAI community | 137M | mit | 15.4M | 1x MI300X, $1.85/hr |
| Qwen3-8B | Qwen | 8.2B | apache-2.0 | 13M | 1x MI300X, $1.85/hr |
| Qwen3-Coder-30B-A3B-Instruct-GGUF | Unsloth AI | — | apache-2.0 | 12.8M | — |
| Qwen2.5-7B-Instruct | Qwen | 7.6B | apache-2.0 | 9.7M | 1x MI300X, $1.85/hr |
| Qwen2.5-0.5B-Instruct | Qwen | 494M | apache-2.0 | 8.5M | 1x MI300X, $1.85/hr |
| Qwen3.6-35B-A3B-NVFP4 | NVIDIA | 18.7B | apache-2.0 | 8.4M | 1x MI300X, $1.85/hr |
| opt-125m | AI at Meta | — | other | 7.5M | — |
| Qwen3-4B | Qwen | 4B | apache-2.0 | 7.2M | 1x MI300X, $1.85/hr |
| OTel-2.0-LLM-31B-IT | Farbod Tavakkoli | 31.3B | apache-2.0 | 7.2M | 1x MI300X, $1.85/hr |
Licenses
| License | Models | Commercial use |
|---|---|---|
| apache-2.0 | 164 | Yes |
| not stated | 51 | Not stated |
| other | 41 | Read the license |
| mit | 41 | Yes |
| llama3 | 13 | Yes, with conditions |
| osl-3.0 | 5 | Read the license |
| llama3.2 | 5 | Read the license |
| gemma | 5 | Yes, with conditions |
Who Publishes Them
| Publisher | Models |
|---|---|
| Convergent Intelligence | 52 |
| Qwen | 42 |
| Kumar | 14 |
| Park | 12 |
| NVIDIA | 11 |
| DeepSeek | 10 |
All 338 Models, Page 6 of 6
STRIDE ablation distributing each response diversity bonus uniformly over its eligible tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global…
GRPO with group-standardized answer correctness, without a STRIDE diversity bonus. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch…
STRIDE with nonnegative local step-diversity credit on eligible reasoning tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is…
STRIDE with nonnegative local step-diversity credit on eligible reasoning tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is…
STRIDE with nonnegative local step-diversity credit on eligible reasoning tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is…
STRIDE with nonnegative local step-diversity credit on eligible reasoning tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is…
STRIDE ablation using one pooled reasoning embedding per eligible response. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global prompt batch is 64…
STRIDE ablation distributing each response diversity bonus uniformly over its eligible tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 8 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 9 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 1 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 2 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 3 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 4 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 5 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 6 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 7 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 8 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises…
tanpo-deals (Deal Cracker) is a compact B2B deal-closing and distributor/channel specialist for practical commercial work—not generic chatbot chatter. This repository contains the merged Transformers fine-tune, ready to load with transformers or Unsloth. Official DarkLab evaluation on the same 20-task deals rubric and decoding setup. tanpo-deals beats the base by +7.3 percentage points. BEATSBASE: YES Automated rubric results are directional; human judgment remains important for consequential commercial decisions. - GGUF for LM Studio / llama.cpp: d4rkninja/tanpo-deals-GGUF — recommend Q4KM Focused on B2B sales, deal closing, wholesale, distributors, channel partners, negotiation, and…
Ready-to-run GGUF quantizations of tanpo-deals, a compact B2B deal-closing and distributor/channel specialist. Open a.gguf in LM Studio, llama.cpp, Ollama, or another GGUF-compatible runtime—no LoRA wiring required. Official DarkLab evaluation on the same 20-task deals rubric and decoding setup. The tanpo-deals fine-tune beats the base by +7.3 percentage points. BEATSBASE: YES Discovery and qualification; objection handling and closing; proposal and ROI; distributor recruiting; channel-partner enablement; wholesale pricing and terms; negotiation tactics; pipeline and forecast hygiene; outreach sequences; and identity/safety guardrails. Automated rubric results are directional; verify…
A compact customer-retention specialist (~1.2B) for onboarding, activation, churn-save, customer-success playbooks, health-score follow-up, renewals, expansion, escalation, identity guardrails, and winback workflows — built for local and inexpensive deployment. Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment). Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT). This repository hosts the merged Transformers weights (LoRA merged into the base). Tanpo is a family of compact domain-specialized business models for local / edge / inexpensive deployment.…
GGUF quantizations of d4rkninja/tanpo-retention for local runtimes (llama.cpp, LM Studio, and other GGUF-compatible tools). Tanpo is a family of compact domain-specialized business models for local / edge / inexpensive deployment. Different specialists cover different workflows. Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment). Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT). A compact customer-retention specialist (~1.2B) for onboarding, activation, churn-save, customer-success playbooks, health-score follow-up, renewals, expansion, escalation…
PEFT LoRA adapter that specializes LiquidAI/LFM2.5-1.2B-Instruct for retention workflows (trained via Unsloth hub id unsloth/LFM2.5-1.2B-Instruct). Tanpo is a family of compact domain-specialized business models for local / edge / inexpensive deployment. Different specialists cover different workflows. Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment). Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT). Full eval, examples, and responsible-use notes: d4rkninja/tanpo-retention. - Onboarding, activation, churn-save, renewal, expansion, escalation, and…
Refusal-ablated Ternary Bonsai 2 27B, edited directly on the ternary lattice and shipped in PrismML's native PTQ10 pack. - 5,946,648,928 bytes — byte-for-byte the size of the official PTQ10 release - No requantization, no BF16 bake, no runtime steering, no control vector at serve time - Requires the PrismML llama.cpp fork Differs from PrismML's release in exactly 98 tensors and nowhere else. The other 753 tensors are byte-identical, including tokenembd and output. Anyone with both files can check that without trusting us. Paired against the untouched PrismML release: same card, same runtime, same flags, same seed, enablethinking: false on both arms. Judge is Qwen3.8-27B-OBLITERATED-Q80 with…
Bonsai 2 27B by Prism ML, repacked for vLLM. Unofficial; not affiliated with Prism ML. It needs the prismternary vLLM plugin from fraserprice/bonsai-vllm, which has the run command, kernels and throughput numbers: Built and tested for the RTX PRO 6000 Blackwell only; other NVIDIA GPUs are untested. Problems: open an issue. - The ternary weights of the MLX pack, bit for bit: the same 2-bit codes and FP16 group scales (g128), in the same Hadamard-rotated basis. MLX's redundant per-group biases (-scale) are dropped, and the rotation signs move into config.json. - The embedding table is dequantized to BF16. - Norms and the linear-attention state path are Prism ML's own tensors from the MLX…
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.21.0
VinaySLM is a small language model (SLM) built from scratch in PyTorch to learn how decoder-only Transformers work end to end -- tokenization, embeddings, causal self-attention, training, and generation -- without importing a pretrained architecture. This is not a production-quality language model. - A tiny, hand-written, decoder-only (GPT-style) Transformer. - 466,176 parameters. - Trained on a ~600-token toy corpus of AI/programming sentences. - Packaged here as a custom Hugging Face model (trustremotecode=True) so it can be loaded and inspected through the transformers ecosystem, while the actual Transformer implementation (modelingvinayslm.py) is a thin wrapper around this project's…
VNPen is MewBaka Studio's visual-novel model series. The writer edition is for script writing, de-AI rewriting, and generating example scenes from a mood brief. Output format is one script line per line: speaker：text, with narration written as 旁白：. The base Qwen/Qwen3.5-2B is multimodal. Its checkpoint carries 297 model.visual. tensors (a depth-24 / hidden-1024 / patch-16 ViT) and 15 mtp. tensors for multi-token prediction. This project is text-only. In transformers, AutoModelForCausalLM on a qwen35 config builds Qwen35ForCausalLM over a Qwen35TextConfig — so the vision weights were never loaded at any point: not for training, not for merging, not for saving. Verified on the published…
a small chat model that talks like a puppygirl and still answers the question. fine-tuned from Qwen/Qwen3.5-2B (Apache-2.0). wag speaks in lowercase, soft, playful puppyspeak — wan~, awoo, arf,:3, the occasional ears perk — and underneath that gives you a real answer. the voice is the product, but the whole point was that it doesn't come at the cost of being useful. the failure mode this was built to avoid is collapsing into pure noise: a model that barks charmingly and tells you nothing. the eval below scores helpfulness and voice separately so that tradeoff stays visible instead of hiding behind vibes. llama.cpp / LM Studio / ollama — grab a quant from gguf/ and go. wag-q4km.gguf is the…
Gemma 4 26B-A4B, post-trained with GRPO against a reward model learned from 1.2 million double-blind votes cast by HiWaifu users inside their own role-play conversations. Put back into the same arena, blind, it met GLM-5.1 in 1,430 battles and won 49.6% of the decided votes; against a 13-model field including Gemini, DeepSeek-v4 and Qwen's character models it won 54.7%. Most open role-play models are tuned on preferences that come from an LLM judge, from a handful of annotators, or from synthetic pairs. We had something rarer: a live arena where, inside ordinary chats on our platform, a user is occasionally shown two candidate replies and asked which one they want to continue with. Those…
Zenyx V3 is an efficient 1.5B-parameter Mixture-of-Experts (MoE) foundation model built for low-latency inference and high throughput. It is written from scratch in JAX/Flax and trained on TPU v5e-8. active per token, with a Sinkhorn transport-based gate. single shared key/value head, plus low-rank query and output projections. stability at scale. YaRN and RoPE scaling factors are precomputed so context can be extended at inference time beyond the trained length. All tasks are evaluated with the standard base-model protocol: the model scores the log-likelihood of every candidate continuation and the highest-scoring one is taken as the answer. Nothing is generated and no output parsing is…
High-efficiency, hardware-tested GGUF releases of Qwen3.8-27B (27 Billion Parameters, Dense Architecture). All models in this repository have been physically converted, verified on hardware (AMD Instinct MI300X with ROCm / HIP), and benchmarked for prompt throughput, token generation velocity, and benchmark accuracy against baseline models. This repository provides three specialized model tiers: - zraldv1-ac (Accuracy-Priority Tier): 17.08 GiB (18.3 GB). Near-lossless retention (99.68% accuracy), matches or outperforms standard Q6K and Q80 quality while saving ~10 GB VRAM compared to Q80. - zraldv1-ba (Balanced Sweet-Spot): 14.46 GiB (15.5 GB). Optimal balance (99.12% accuracy), fits…
Official high-efficiency GGUF release of Qwen3.8-27B optimized for Accuracy Priority Tier. This repository contains zraldv1-ac.gguf (17.08 GiB / 18.34 GB), physically benchmarked on AMD Instinct MI300X hardware. For cross-comparison tables against standard Q80, Q6K, Q5K, Q4K, and Q2K models, visit the master repository: - Base model by the Qwen Team (Alibaba) under Apache 2.0. - Runtime by Georgi Gerganov and the llama.cpp community.
Official high-efficiency GGUF release of Qwen3.8-27B optimized for Balanced Sweet-Spot Tier. This repository contains zraldv1-ba.gguf (14.46 GiB / 15.52 GB), physically benchmarked on AMD Instinct MI300X hardware. For cross-comparison tables against standard Q80, Q6K, Q5K, Q4K, and Q2K models, visit the master repository: - Base model by the Qwen Team (Alibaba) under Apache 2.0. - Runtime by Georgi Gerganov and the llama.cpp community.
Official high-efficiency GGUF release of Qwen3.8-27B optimized for Compressed Size Tier. This repository contains zraldv1-cs.gguf (10.18 GiB / 10.93 GB), physically benchmarked on AMD Instinct MI300X hardware. For cross-comparison tables against standard Q80, Q6K, Q5K, Q4K, and Q2K models, visit the master repository: - Base model by the Qwen Team (Alibaba) under Apache 2.0. - Runtime by Georgi Gerganov and the llama.cpp community.
Questions
Which Text generation models are most downloaded?
By monthly downloads reported by the Hugging Face Hub: .