reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
Qwen3-0.6B-Distilled-30B-A3…/README.md

224 lines
9.3 KiB
Markdown
Raw Permalink Normal View History

初始化项目，由ModelHub XC社区提供模型 Model: reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF Source: Original Platform
2026-04-12 14:14:57 +08:00
---
library_name: llama.cpp
license: apache-2.0
language:
- en
base_model: reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT
tags:
- gguf
- quantized
- distillation
- sft
- reasoning
- mathematics
- physics
- legal
- stem
- chain-of-thought
- edge
- mobile
- convergentintel
- knowledge-distillation
pipeline_tag: text-generation
---
# Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT — GGUF
GGUF quantizations of [reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT) for local, mobile, and edge deployment via [llama.cpp](https://github.com/ggerganov/llama.cpp) and compatible runtimes.
A 30B Thinking teacher compressed 50x into a model that fits on a smartwatch.
## Available Quantizations
| File | Quant | Size | Use Case |
|---|---|---|---|
| `qwen3-0.6b-distilled-30b-thinking-sft-f16.gguf` | F16 | ~1.3 GB | Full precision reference |
| `qwen3-0.6b-distilled-30b-thinking-sft-Q8_0.gguf` | Q8_0 | ~700 MB | Near-lossless, desktop/laptop |
| `qwen3-0.6b-distilled-30b-thinking-sft-Q5_K_M.gguf` | Q5_K_M | ~500 MB | Balanced, mobile |
| `qwen3-0.6b-distilled-30b-thinking-sft-Q4_K_M.gguf` | Q4_K_M | ~400 MB | Smallest, IoT/edge/smartwatch |
**Recommended:** Q5_K_M for mobile, Q4_K_M for maximum compression.
## About the Model
Two-stage build:
**Stage 1 — Thinking Teacher Distillation:** Qwen3-0.6B distilled from Qwen3-30B-A3B-Thinking on 6,122 STEM chain-of-thought samples. The Thinking variant teacher produces extended reasoning traces with higher-entropy distributions, transferring richer deliberation structure into the student. Proof-weighted cross-entropy (2.5x → 1.5x on derivation tokens) + KL divergence at T=2.0.
**Stage 2 — Legal SFT:** Supervised fine-tuning on [Alignment-Lab-AI/Lawyer-Instruct](https://huggingface.co/datasets/Alignment-Lab-AI/Lawyer-Instruct) at conservative learning rate (5e-6) to layer legal reasoning on top of the STEM backbone without overwriting it.
| Attribute | Value |
|---|---|
| **Base model** | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) |
| **Teacher model** | [Qwen/Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507) |
| **Compression** | 50x parameters, ~75x with Q4_K_M |
| **Developer** | Reaperdoesntrun / [Convergent Intelligence LLC](https://convergentintel.com): Research Division |
## Usage
### llama.cpp CLI
```bash
./llama-cli -m qwen3-0.6b-distilled-30b-thinking-sft-Q4_K_M.gguf \
-p "### Instruction:\nWhat is promissory estoppel?\n\n### Response:\n" \
-n 512 --temp 0.0
```
### llama.cpp Python
```python
from llama_cpp import Llama
llm = Llama(model_path="qwen3-0.6b-distilled-30b-thinking-sft-Q4_K_M.gguf", n_ctx=1024)
output = llm(
"### Instruction:\nProve that the square root of 2 is irrational.\n\n### Response:\n",
max_tokens=512,
temperature=0.0,
)
print(output["choices"][0]["text"])
```
### Ollama
```bash
echo 'FROM ./qwen3-0.6b-distilled-30b-thinking-sft-Q4_K_M.gguf' > Modelfile
ollama create stem-legal-tiny -f Modelfile
ollama run stem-legal-tiny "Explain the difference between a felony and a misdemeanor."
```
### LM Studio
Download any GGUF file from this repo and load directly in [LM Studio](https://lmstudio.ai/).
## Prompt Formats
**STEM derivation (Stage 1):**
```
Solve the following problem carefully and show a rigorous derivation.
Problem:
[Your problem]
Proof:
```
**Instruction-following (Stage 2):**
```
### Instruction:
[Your question]
### Response:
```
## Limitations
0.6B is a hard capacity constraint. The model trades depth for deployability — it will make errors that larger models avoid. Multi-step proofs beyond ~8 steps degrade. Legal reasoning covers general concepts but lacks nuance. Always verify critical outputs. This is not a substitute for formal proof verification, licensed legal counsel, or professional analysis.
## Source Model
Full training methodology, hyperparameters, and the two-stage pipeline are documented in:
**[reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT)**
## Mathematical Foundations
This is a GGUF-quantized variant. The mathematical foundations (Discrepancy Calculus, Topological Knowledge Distillation) are documented in the source model's card. The discrepancy operator $Df(x)$ and BV decomposition that inform the training pipeline are preserved through quantization — the structural boundaries detected by DISC during training are baked into the weights, not dependent on precision.
## Related Models
| Model | Description |
|---|---|
| [Qwen3-0.6B-STEM-Proof-Distilled-Thinking](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-STEM-Proof-Distilled-Thinking) | Stage 1 only — pure STEM backbone |
| [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT) | Full precision source model |
| [Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF) | Larger 1.7B variant GGUF |
## Citation
```bibtex
@misc{colca2026thinking06bgguf,
title={Qwen3-0.6B Distilled Thinking SFT: 50x Compression GGUF for Edge Deployment},
year={2026},
publisher={HuggingFace},
url={https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF},
note={Convergent Intelligence LLC: Research Division}
}
```
---
*Convergent Intelligence LLC: Research Division*
*"Where classical analysis fails to see, we begin."*
---
## Convergent Intelligence Portfolio
*Part of the [Qwen3 0.6B Distillation Series](https://huggingface.co/reaperdoesntknow) by [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow)*
#
## Mathematical Foundations
This is a GGUF-quantized variant. The mathematical foundations (Discrepancy Calculus, Topological Knowledge Distillation) are documented in the source model's card. The discrepancy operator $Df(x)$ and BV decomposition that inform the training pipeline are preserved through quantization — the structural boundaries detected by DISC during training are baked into the weights, not dependent on precision.
## Related Models
| Model | Downloads | Format |
|-------|-----------|--------|
| [Qwen3-0.6B-Distilled-30B-A3B](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B) | 36 | HF |
| [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT) | 33 | HF |
### Top Models from Our Lab
| Model | Downloads |
|-------|-----------|
| [Qwen3-1.7B-Thinking-Distil](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Thinking-Distil) | 501 |
| [LFM2.5-1.2B-Distilled-SFT](https://huggingface.co/reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT) | 342 |
| [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) | 302 |
| [Qwen3-1.7B-Coder-Distilled-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF) | 194 |
| [Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF) | 175 |
**Total Portfolio: 41 models | 2,781 total downloads**
*Last updated: 2026-03-28 12:49 UTC*
<!-- DISTILQWEN-SPOTLIGHT-START -->
## DistilQwen Collection
This model is part of the **[DistilQwen](https://huggingface.co/collections/reaperdoesntknow/distilqwen-69bf40ec669117e3f069ef1c)** proof-weighted distillation series.
Collection: **9 models** | **2,788 downloads**
### Teacher Variant Comparison
| Teacher | Student Size | Strength | Models |
|---------|-------------|----------|--------|
| Qwen3-30B-A3B (Instruct) | 1.7B | Instruction following, structured output, legal reasoning | 3 (833 DL) |
| Qwen3-30B-A3B (Thinking) | 0.6B | Extended deliberation, higher-entropy distributions, proof derivation | 3 (779 DL) **← this model** |
| Qwen3-30B-A3B (Coder) | 1.7B | Structured decomposition, STEM derivation, logical inference | 2 (825 DL) |
### Methodology
**The only BF16 collection in the portfolio.** While the broader Convergent Intelligence catalog (43 models, 12,000+ downloads) was trained on CPU at FP32 for $24 total compute, the DistilQwen series was trained on H100 at BF16 with a 30B-parameter teacher. Same methodology, premium hardware. This is what happens when you give the pipeline real compute.
All models use proof-weighted knowledge distillation: 55% cross-entropy with decaying proof weights (2.5× → 1.5×), 45% KL divergence at T=2.0. The proof weight amplifies loss on reasoning-critical tokens, forcing the student to allocate capacity to structural understanding rather than surface-level pattern matching.
Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org/10.57967/hf/8165)
### Related in this series
- [Qwen3-0.6B-Distilled-30B-A3B](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B) (236 downloads)
- [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT) (227 downloads)
<!-- DISTILQWEN-SPOTLIGHT-END -->
---
<sub>Part of the [reaperdoesntknow research portfolio](https://huggingface.co/reaperdoesntknow) — 49 models, 22,598 total downloads | Last refreshed: 2026-03-30 12:05 UTC</sub>
<!-- cix-keeper-ts:2026-04-11T16:09:09Z -->
<!-- card-refresh: 2026-03-30 -->
Reference in New Issue Copy Permalink