GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
reaperdoesntknow
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
reaperdoesntknow
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
Qwen3-0.6B distilled from 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.
Why the Thinking teacher matters at 0.6B: The Thinking variant produces higher-entropy softmax distributions than the Instruct variant — it considers more reasoning paths before committing. At distillation temperature T=2.0, the 0.6B student sees a richer landscape of alternative derivation strategies. With only 0.6B parameters, every bit of transferred structure counts. The Thinking teacher gives more.
Data: 6,122 STEM chain-of-thought samples across 12 domains:
| Domain | Samples |
|---|---|
| Physics | 2,254 |
| Linear Algebra | 667 |
| Differential Equations | 636 |
| Electromagnetism | 580 |
| Mathematics | 576 |
| Engineering | 574 |
| Classical Mechanics | 343 |
| Theoretical Mechanics | 307 |
| Advanced Calculus | 268 |
| Modern Physics | 177 |
| Physiology | 114 |
| Molecular Biology | 71 |
All from 0xZee. Shuffled seed 42, split 95/5 train/eval.
Loss function:
Training format:
markdown
Solve the following problem carefully and show a rigorous derivation.Problem:{question}Proof:{CoT}Final Answer:{response}
Stage 1 hyperparameters:
| Parameter | Value |
|---|---|
| Epochs | 1 |
| Training samples | 5,815 |
| Effective batch size | 8 |
| Learning rate | 1.5e-5 → 1e-6 (cosine) |
| Temperature | 2.0 |
| Proof weight | 2.5 → 1.5 |
| Precision | bf16 |
The distilled model was fine-tuned on Alignment-Lab-AI/Lawyer-Instruct using TRL's SFTTrainer.
Why legal on top of STEM: Legal reasoning is structurally isomorphic to mathematical reasoning — premise identification, logical chaining, exception handling, structured argumentation toward a conclusion. A model that learned rigorous derivation transfers that structure to legal analysis rather than learning legal templates from scratch.
Training format:
markdown
### Instruction:{instruction}### Response:{output}
Stage 2 hyperparameters:
| Parameter | Value |
|---|---|
| Epochs | 1 |
| Effective batch size | 8 |
| Learning rate | 5e-6 (lower than Stage 1 to preserve backbone) |
| Gradient checkpointing | Enabled |
| Precision | bf16 |
| Attribute | Value |
|---|---|
| Architecture | Qwen3 (causal LM, RoPE, GQA) |
| Parameters | 0.6B |
| Base model | Qwen/Qwen3-0.6B |
| Teacher model | Qwen/Qwen3-30B-A3B-Thinking-2507 |
| Compression ratio | 50x |
| Stage 1 data | 6,122 STEM CoT samples (12 datasets) |
python
from transformers import AutoTokenizer, AutoModelForCausalLMimport torchmodel_id = "reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,device_map="auto",)# Legal instruction-followingprompt = """### Instruction:What is the difference between a felony and a misdemeanor?### Response:"""# STEM derivation (Stage 1 format still works)prompt_stem = """Solve the following problem carefully and show a rigorous derivation.Problem:Compute the determinant of the matrix [[1, 2], [3, 4]].Proof:"""inputs = tokenizer(prompt, return_tensors="pt").to(model.device)with torch.no_grad():outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Quantized versions at reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF.
STEM derivation (Stage 1):
markdown
Solve the following problem carefully and show a rigorous derivation.Problem:[Your problem]Proof:
Instruction-following (Stage 2):
markdown
### Instruction:[Your question]### Response:
Good for: Ultra-lightweight reasoning on mobile/edge/IoT, legal and STEM instruction-following, educational tutoring, embedded inference, component in multi-model pipelines, anywhere you need reasoning in under 500MB.
Not for: Formal proof verification, actual legal counsel, safety-critical analysis, complex multi-step proofs (>8 steps), or long-context tasks beyond 1024 tokens.
0.6B is a hard capacity constraint. The model trades depth for deployability. It will make reasoning errors that a larger model would not. Multi-step derivations beyond ~8 steps degrade. Legal reasoning covers general concepts but lacks the nuance of larger models. Performance is weakest on underrepresented domains (molecular biology, physiology). Always verify outputs.
This model is part of a distillation chain built on Discrepancy Calculus — a measure-theoretic framework where the teacher's output distribution is decomposed via the Mesh Fundamental Identity into smooth (AC), jump, and Cantor components. The discrepancy operator Df(x)=limε↓0ε1∫xx+ε quantifies local structural mismatch that standard KL divergence averages away.
Full theory: "On the Formal Analysis of Discrepancy Calculus" (Colca, 2026; Convergent Intelligence LLC: Research Division). Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165).
| Model | Description |
|---|---|
| Qwen3-0.6B-STEM-Proof-Distilled-Thinking | Stage 1 only — pure STEM backbone |
| Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF | This model quantized for edge deployment |
| Qwen3-1.7B-STEM-Proof-Distilled | Larger 1.7B variant (Instruct teacher) |
| Qwen3-1.7B-Distilled-30B-A3B-SFT | Larger 1.7B variant + legal SFT |
bibtex
@misc{colca2026thinking06bsft,title={Two-Stage Reasoning Transfer at 0.6B: Thinking Teacher Distillation + Legal SFT},year={2026},publisher={HuggingFace},url={https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT},note={Convergent Intelligence LLC: Research Division}}
Convergent Intelligence LLC: Research Division "Where classical analysis fails to see, we begin."
Part of the Qwen3 0.6B Distillation Series by Convergent Intelligence LLC: Research Division
This model is part of a distillation chain built on Discrepancy Calculus — a measure-theoretic framework where the teacher's output distribution is decomposed via the Mesh Fundamental Identity into smooth (AC), jump, and Cantor components. The discrepancy operator Df(x)=limε↓0ε1∫xx+ε quantifies local structural mismatch that standard KL divergence averages away.
Full theory: "On the Formal Analysis of Discrepancy Calculus" (Colca, 2026; Convergent Intelligence LLC: Research Division). Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165).
| Model | Downloads | Format |
|---|---|---|
| Qwen3-0.6B-Distilled-30B-A3B | 36 | HF |
| Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF | 203 | GGUF |
| Model | Downloads |
|---|---|
| Qwen3-1.7B-Thinking-Distil | 501 |
| LFM2.5-1.2B-Distilled-SFT | 342 |
| Qwen3-1.7B-Coder-Distilled-SFT | 302 |
| Qwen3-1.7B-Coder-Distilled-SFT-GGUF | 194 |
| Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF |
Total Portfolio: 41 models | 2,781 total downloads
Last updated: 2026-03-28 12:56 UTC
This model is part of the DistilQwen proof-weighted distillation series. Collection: 9 models | 2,788 downloads
| 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) |
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)
| Alignment-Lab-AI/Lawyer-Instruct |
| Context length | 1024 tokens (training) |
| License | Apache 2.0 |
| Developer | Reaperdoesntrun / Convergent Intelligence LLC: Research Division |
| 175 |