DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K needs about 4.1 GB of memory at Q8_0 (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K – a compact 3.09B parameter instruction model
This model is a 3.09 billion parameter Qwen2 architecture distilled from DeepSeek. It supports reasoning and tool usage. The GGUF file is 3.29 GB and requires about 4.1 GB of VRAM at 8 k context.
Good at
- Reasoning tasks
- Tool invocation
- Instruction following
Limits
- No vision support
- Limited context to 32 768 tokens
- No license information
Best for
- Chatbot prototypes
- Lightweight inference on GPUs
- Educational demos
Who it’s for. Developers needing a small, instruction‑oriented model for local deployment. It is suitable for projects that require reasoning and tool use without large memory footprints.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → |
The only available quant is Q8_0, 3.29 GB in size. It needs roughly 4.1 GB of VRAM at 8 k context. For 8 GB VRAM users, this quant is suitable. No other quants are provided.
What GPU do you need for DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
Which DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K quant should you choose?
Q8_0 (3.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K
How much VRAM does DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K need?
About 4.1 GB at Q8_0 with an 8K context window. That is the 3.3 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 DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K on an 8 GB GPU?
Yes, with Q8_0: the 3.3 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K GGUF?
It depends on the quant: Q8_0 is 3.3 GB.
What context length does DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download DeepSeek R1 Distill Qwen2.5 3B Instruct BS17K GGUF?
The files are on Hugging Face in the eggbiscuit/DeepSeek-R1-Distill-Qwen2.5-3B-Instruct-BS17K repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the Q8_0 quant requires about 4.1 GB of VRAM at 8 k context, fitting within an 8 GB GPU.
Does this model support vision?
No, it does not have vision capabilities.
What is the context length?
The model supports up to 32 768 tokens.