Qwen3 1.7B Distilled 30B A3B SFT needs about 2.7 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.3 GB (Q4_K_M) to 4.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Qwen3 1.7B Distilled 30B A3B SFT – structured reasoning and legal instruction
Qwen3 1.7B Distilled 30B A3B SFT is a 2.03 billion‑parameter model trained in two stages: knowledge distillation from a 30B MoE teacher on STEM chain‑of‑thought data, then supervised fine‑tuning on legal instruction. It is available in GGUF format for local deployment via llama.cpp.
Good at
- STEM reasoning with structured derivations
- Legal instruction following
- Instruction‑following on small devices
Limits
- No vision support
- Limited to 40960 context tokens
- Requires Apache‑2.0 license compliance
Best for
- Physics problem solving
- Legal document drafting
- Instruction‑based chatbot on edge devices
Who it’s for. Developers building lightweight reasoning assistants for mobile or edge hardware. Researchers needing a small model with proven structured reasoning capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.5 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 2.2 GB | 3.6 GB | Fits | Get file → | |
| F16 | 4.1 GB | 5.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q5_K_M (1.47 GB file, ~2.9 GB VRAM at 8 k context). For 4 GB VRAM, use Q4_K_M (1.28 GB file, ~2.7 GB VRAM at 8 k context). Higher precision F16 (4.07 GB file) needs ~5.5 GB VRAM.
What GPU do you need for Qwen3 1.7B Distilled 30B A3B 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 Q8_0 (2.2 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.1 GB file, about 5.5 GB in use).
Which Qwen3 1.7B Distilled 30B A3B SFT quant should you choose?
Q4_K_M is the usual starting point for Qwen3 1.7B Distilled 30B A3B SFT: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.2 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 1.7B Distilled 30B A3B SFT
How much VRAM does Qwen3 1.7B Distilled 30B A3B SFT need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.3 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 1.7B Distilled 30B A3B SFT on an 8 GB GPU?
Yes, with F16: the 4.1 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 1.7B Distilled 30B A3B SFT GGUF?
It depends on the quant: Q4_K_M is 1.3 GB, Q5_K_M is 1.5 GB, Q8_0 is 2.2 GB, F16 is 4.1 GB.
What context length does Qwen3 1.7B Distilled 30B A3B 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 1.7B Distilled 30B A3B SFT GGUF?
The files are on Hugging Face in the reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-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 1.7B Distilled 30B A3B 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 1.7B Distilled on 8 GB VRAM?
Yes, the Q5_K_M quantization uses about 2.9 GB VRAM at 8 k context, leaving headroom for other processes.
Does this model support image input?
No, the model has no vision capabilities and only processes text.
What license applies to this model?
The model is released under the Apache‑2.0 license.