Qwen3 0.6B Distilled 30B A3B Thinking SFT needs about 1.9 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.5 GB (Q4_K_M) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Qwen3 0.6B Distilled 30B A3B Thinking SFT – a compact reasoning model
Qwen3 0.6B Distilled 30B A3B Thinking SFT is a 0.6B parameter model built through knowledge distillation from a 30B Thinking teacher and legal instruction fine‑tuning. It supports 40960 token context and is released under apache‑2.0.
Good at
- Reasoning with chain‑of‑thought
- Legal instruction following
- STEM problem solving
Limits
- No vision support
- Limited multi‑step proofs beyond ~8 steps
- Requires 8k context for memory estimates
Best for
- Mobile reasoning apps
- Legal document drafting assistants
- Educational STEM tutoring
Who it’s for. Developers and researchers needing a small, reasoning‑oriented LLM for edge deployment. It is suitable for mobile or smartwatch use where memory is constrained.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.5 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 2.2 GB | Fits | Get file → | |
| F16 | 1.5 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM use Q5_K_M (file size 0.55 GB, ~2 GB memory at 8k context). For 4 GB VRAM use Q4_K_M (0.48 GB, ~1.9 GB memory). If more VRAM is available, Q8_0 or F16 offer higher precision.
What GPU do you need for Qwen3 0.6B Distilled 30B A3B Thinking SFT?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (1.5 GB file, about 2.9 GB in use).
Which Qwen3 0.6B Distilled 30B A3B Thinking SFT quant should you choose?
Q4_K_M is the usual starting point for Qwen3 0.6B Distilled 30B A3B Thinking SFT: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3 0.6B Distilled 30B A3B Thinking SFT
How much VRAM does Qwen3 0.6B Distilled 30B A3B Thinking SFT need?
About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Qwen3 0.6B Distilled 30B A3B Thinking SFT on an 8 GB GPU?
Yes, with F16: the 1.5 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 0.6B Distilled 30B A3B Thinking SFT GGUF?
It depends on the quant: Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q8_0 is 0.8 GB, F16 is 1.5 GB.
What context length does Qwen3 0.6B Distilled 30B A3B Thinking SFT support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Qwen3 0.6B Distilled 30B A3B Thinking SFT GGUF?
The files are on Hugging Face in the reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen3 0.6B Distilled 30B A3B Thinking SFT use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Qwen3 0.6B Distilled on 4 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 1.9 GB memory at 8k context.
Does this model support image inputs?
No, it has no vision capabilities.
What context length does it support?
It supports up to 40960 tokens.