# Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT by Convergent Source: https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b-thinking-sft Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT (752M 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 | 1.5 GB | 1.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.8 GB | 0.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.4 GB | 0.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b-thinking-sft/gpus) ## Model Card By Convergent Intelligence, published under apache-2.0, revision 2d000dca1c12. A 0.6B parameter model built in two stages: knowledge distillation from a 30B Thinking teacher to establish a structured reasoning backbone, then supervised fine-tuning on legal instruction data. 50x compression. Under 500MB quantized. Runs on a phone. The training order is the thesis: teach the model how to reason first (distillation from Thinking teacher), then teach it what to reason about (legal SFT). The Thinking teacher's extended deliberation traces transfer deeper reasoning structure than an Instruct teacher — critical when the student has only 0.6B parameters to work with. "Structure beats scale, collaboration beats hierarchy, observation beats theory." — Convergent Intelligence LLC: Research Division ### Training Pipeline #### Stage 1: Knowledge Distillation (STEM Reasoning Backbone) Qwen3-0.6B distilled from [Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507) — a Mixture-of-Experts model with 30B total parameters, ~3B active per token, using the Thinking variant that generates extended internal reasoning traces. [Read the full model card (1,197 words)](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b-thinking-sft/card) ## Configuration Architecture Qwen3ForCausalLM Context length (tokens) 40,960 Layers 28 Hidden size 1,024 Feed-forward size 3,072 Attention heads 16 Key/value heads 8 Head dimension 128 Vocabulary size 151,936 Model type qwen3 ## Identity and Version Repository reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT Publisher Convergent Intelligence Task Text generation Modality Text Library transformers Parameters 752M parameters Languages en Revision 2d000dca1c123027b5313c99fe6c07366ab7de6b First published 2026-03-22 Last updated 2026-09-18 ## Files and Weights 8 files, 1.5 GB in total. The weights are 1 file totalling 1.5 GB in safetensors. Weights1 file · 1.5 GB Configuration2 files · 1.6 KB Tokenizer2 files · 11.4 MB Documentation1 file · 13.5 KB Other1 file · 4.2 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 1.5 GB | c1d2b15ffb42 | | config.json | Configuration | 1.4 KB | — | | generation_config.json | Configuration | 187 B | — | | README.md | Documentation | 13.5 KB | — | | chat_template.jinja | Other | 4.2 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 11.4 MB | be75606093db | | tokenizer_config.json | Tokenizer | 665 B | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 1.5 GB [Download from Convergent Intelligence](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT) Released by Convergent Intelligence through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [Qwen/Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) - Trained on (disclosed) 0xZee/dataset-CoT-Advanced-Calculus-268 - Trained on (disclosed) 0xZee/dataset-CoT-Classical-Mechanics-343 - Trained on (disclosed) 0xZee/dataset-CoT-Differential-Equations-636 - Trained on (disclosed) 0xZee/dataset-CoT-Electromagnetism-580 - Trained on (disclosed) 0xZee/dataset-CoT-Engineering-574 - Trained on (disclosed) 0xZee/dataset-CoT-Linear-Algebra-667 - Trained on (disclosed) 0xZee/dataset-CoT-Modern-Physics-177 - Trained on (disclosed) 0xZee/dataset-CoT-Molecular-Biology-71 - Trained on (disclosed) 0xZee/dataset-CoT-Physics-2254 - Trained on (disclosed) 0xZee/dataset-CoT-Physiology-114 - Trained on (disclosed) 0xZee/dataset-CoT-Theoretical-Mechanics-307 - Trained on (disclosed) 0xZee/dataset-CoT-mathematics - Trained on (disclosed) Alignment-Lab-AI/Lawyer-Instruct ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.5 GB | | 16-bit | 1.5 GB | | 8-bit | 0.8 GB | | 4-bit | 0.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Quantized from[Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b-thinking-sft-gguf) - Derived from[Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b-thinking-sft-gguf) ## Questions About Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT ### How much GPU memory does Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT need? About 1.8 GB at 16-bit and 0.5 GB at 4-bit: the weights (752M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT on? 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. ### Can I use Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT commercially? Yes. Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT's context length? 40,960 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and… Open weights apache-2.0 752M parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-0-6b) Model · Text generation ### [Qwen3-0.6B-Distilled-30B-A3B](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) A 0.6B parameter model distilled from Qwen3-30B-A3B-Thinking on 6,122 STEM chain-of-thought samples. 50x parameter compression. The Thinking variant teacher produces richer extended reasoning traces than the Instruct variant, transferring deeper deliberation structure into the smallest possible student. The result: a model under 500MB quantized that produces structured STEM derivations because a 30B thinking model showed it how to reason. Two key differences from standard small-model distillation: 1. Thinking teacher, not Instruct teacher. The Qwen3-30B-A3B-Thinking variant generates extended internal reasoning before committing to an answer. Its softmax distributions are higher-entropy… Open weights apache-2.0 752M parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b) Model · Text generation ### [stream-1-mini](https://savrn.com/models/stream-1-mini) [Whisperstream](https://savrn.com/model-publishers/whisperstream) Stream-1 Mini turns English dictation transcripts into clean Chat and Email text on your own device. It is trained to remove fillers and accidental repeats, add punctuation, and resolve spoken corrections while preserving your meaning and voice. Email mode also formats dictated greetings, paragraphs and sign-offs. This revision adds optional custom-vocabulary hints while retaining structural dictation and numbered-list support. Use these prompts and weights together. Candidates are spelling hints, not forced substitutions. Known cleanup and entity errors remain; this revision does not establish zero regressions. Pass in text from your speech recognizer. Stream-1 Mini returns the cleaned… Open weights other 752M parameters 32,768 tokens [View model](https://savrn.com/models/stream-1-mini) Model · Text generation ### [Qwen3-Coder-Next-CQ-4bit](https://savrn.com/models/qwen3-coder-next-cq-4bit) [ThousandML](https://savrn.com/model-publishers/thousandml) Qwen3-Coder-Next quantized to 4-bit with Coded Quantization (CQ). CQ is a calibration-free 4-bit quantization method designed to preserve the behavior of the original model without requiring a calibration dataset. Because CQ does not optimize the quantization around a fixed calibration corpus, it is designed to generalize beyond calibration-specific data and workloads. This repository contains Qwen3-Coder-Next quantized with Coded Quantization (CQ) 4-bit. Calibration-free. CQ does not require a representative calibration dataset before quantization. This avoids tying the quantization procedure to a particular calibration corpus and is intended to provide better generalization beyond the… Open weights apache-2.0 752M parameters 262,144 tokens [View model](https://savrn.com/models/qwen3-coder-next-cq-4bit) Model · Text generation ### [dQwen3.5-0.8B-Base](https://savrn.com/models/dqwen3-5-0-8b-base) [IFML](https://savrn.com/model-publishers/ut-ifml) A masked diffusion language model adapted from Qwen3.5-0.8B. The backbone is hybrid: only its attention layers are made bidirectional, and the Gated DeltaNet layers stay causal. This is a base model, with no instruction tuning. Paper: dQwen3.5: Hybrid-Attention Diffusion Language Models. Code: https://github.com/AntonXue/dQwen Needs a CUDA GPU and transformers>=5.13 (tested with torch 2.7.1+cu128, flash-linear-attention 0.5.1). generate decodes the whole canvas at once, committing positions above a confidence threshold (tau=0.9); pass blocklength=32 for left-to-right block decoding, or tau=None, stepsperblock=k for a fixed budget. The 50B-token checkpoint from the paper is… Open weights apache-2.0 752M parameters 262,144 tokens transformers [View model](https://savrn.com/models/dqwen3-5-0-8b-base) Model · Text generation ### [szl-receiptagent-qwen35-0.8b-v3](https://savrn.com/models/szl-receiptagent-qwen35-0-8b-v3) [SZL Holdings](https://savrn.com/model-publishers/szlholdings) This is a separate research bf16 LoRA adapter (r=16, alpha=32) on Qwen/Qwen3.5-0.8B, trained with Unsloth on a laptop Blackwell GPU, with a derived merged artifact also present in the repository. "Placeholder" describes release status, not absence of weights. It does not overwrite ReceiptAgent v2 Sizes were read from the Hub listing; no weight file was downloaded or hashed by this pass, and the revision SHA was not captured. The Hub-hosted banner referenced by the szl-forge card (holo-banner.svg) is not on this tree, so it is not embedded here. The training receipt records 180 training rows and train loss 0.0537. Training loss is not evaluation. The receipt describes the local laptop… Open weights apache-2.0 752M parameters 262,144 tokens peft [View model](https://savrn.com/models/szl-receiptagent-qwen35-0-8b-v3) ## Convergent Intelligence [All models and datasets](https://savrn.com/model-publishers/reaperdoesntknow) ## Versions - [2d000dca1c12](https://savrn.com/models/qwen3-0-6b-distilled-30b-a3b-thinking-sft/versions/2d000dca1c12) · current 2026-09-18 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-21. - [Hugging Face record](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT) - [How the hub is built](https://savrn.com/model-hub/methodology)