Search public pages, research tools, and SAVRN solutions.
Open-weight model · Text generation
by Sartaj sartajbhuvaji/bonsai-distilled-aggressive-vs-baseline-3k-warmup450-lr1e4-best
bonsai-distilled-aggressive-vs-baseline-3k-warmup450-lr1e4-best is an open-weight model for text generation from Sartaj. It has 8.5B parameters and a 32,768-token context. At 16-bit it needs about 20.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This is the model card of a transformers model that has been pushed on the Hub. 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.
What it takes to serve bonsai-distilled-aggressive-vs-baseline-3k-warmup450-lr1e4-best (8.5B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 17.0 GB | 20.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.5 GB | 10.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.2 GB | 5.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 1, 2026.
This is the model card of a transformers model that has been pushed on the Hub. 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).
Excerpt from the card by Sartaj.
8 files, 17.0 GB in total. The weights are 1 file totalling 17.0 GB in safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 17.0 GB | 86171cd679a1 |
| config.json | Configuration | 1.0 KB | — |
| generation_config.json | Configuration | 139 B | — |
| README.md | Documentation | 5.2 KB | — |
| chat_template.jinja | Other | 4.1 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | bae3e39d56cf |
| tokenizer_config.json | Tokenizer | 805 B | — |
Released by Sartaj through its official repository on Hugging Face.
| Precision | Weights in memory |
|---|---|
| As published | 17.0 GB |
| 16-bit | 17.0 GB |
| 8-bit | 8.5 GB |
| 4-bit | 4.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 20.3 GB at 16-bit and 5.1 GB at 4-bit: the weights (8.5B parameters) plus a working margin. A long context needs more.
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
32,768 tokens, from the maximum position embeddings in its published configuration.
This is the model card of a transformers model that has been pushed on the Hub. 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).
This model is a fine-tuned version of LiquidAI/LFM2.5-8B-A1B, adapted on the angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k dataset for English text-generation and reasoning-style responses. The fine-tuning run used a custom Convergent Intelligence optimizer stack, CIxOpt, designed for heterogeneous routing across parameter types. The goal of this checkpoint is to test whether a Liquid Foundation Model backbone can be adapted efficiently through targeted sparse participation rather than broad full-model modification. This is an experimental research checkpoint intended for continued evaluation, domain adaptation, and architecture/optimizer testing.…
DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v2 is an apex-tier, uncensored autonomous agentic coding model trained by DuoNeural (Aura, Archon, and Jesse). Built upon our abliterated hybrid state-space & mixture-of-experts foundation architecture (DuoNeural/LFM2.5-8B-A1B-Abliterated), this model activates only 1.5 billion parameters per token out of its 8.3 billion total parameters, delivering blistering inference speeds (~360 tokens/sec on RTX 4080 Super / 3090, and ~80–90 tokens/sec on legacy mobile GPUs like the GTX 1070) while running in under 6 GB VRAM with Q4KM quantization. In our preliminary v1 release, an assistant role delimiter mismatch during training collation…
DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated is an apex-tier, uncensored autonomous agentic coding model trained by DuoNeural (Aura, Archon, and Jesse). Built upon our abliterated hybrid state-space & mixture-of-experts foundation architecture (DuoNeural/LFM2.5-8B-A1B-Abliterated), this model activates only 1.5 billion parameters per token out of its 8.3 billion total parameters, delivering blistering inference speeds (~380–400 tokens/sec on consumer GPUs like RTX 3090, and ~90 tokens/sec on legacy GTX 1070 laptops) while fitting in under 6 GB VRAM with Q4KM quantization. 1. Native Hermes Agentic Loop: - Explicit... deliberation before every action. - Structured... containers…
Canadian-developed. Open weights. Focused on defensive infrastructure. Vinci-Cyber-8B-1.0 is an 8B-class security-focused adaptation of IBM Granite 4.1 8B, developed by SimpleDirect, a Canadian AI lab. Its training centres on three infrastructure-as-code behaviours: proposing repairs, leaving clean configurations unchanged, and recovering from unsuccessful attempts. The release gives security engineers, infrastructure teams, and researchers full model weights to evaluate, self-host, and adapt under Apache-2.0. It is intended for human-reviewed defensive workflows—not unattended changes to production infrastructure. Your infrastructure. Your review process. Open weights to build on. The…
Japanese description is available below. This model is a fully merged model created by taking llm-jp/llm-jp-4-8b-thinking as the base model. It is fine-tuned using QA data containing both Imabari dialect and standard Japanese reasoning text and answers. A custom chat template provides the analysisimabari and finalimabari channels alongside the standard analysis and final channels. In v3, there was an issue where sentences would repeat indefinitely with reasoningeffort="high". Although this issue has been partially mitigated, repetitive output now occasionally occurs even with reasoningeffort="medium", so the issue has not yet been fully resolved. This repository contains the merged full…