DeepSeek V2.5 needs about 183.2 GB of memory at Q4_K_M (a 142.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 17 quants, from 52.7 GB (IQ1_M) to 250.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 161.1 GB.
DeepSeek V2.5 – a 236‑billion‑parameter model with coding and chat capabilities
DeepSeek V2.5 combines the general chat and coding abilities of its predecessors. It supports up to 163,840 context tokens and is available in multiple GGUF quantizations. The model is released under a permissive license and can be run locally with llama.cpp or vLLM.
Good at
- Chat and instruction following
- Coding assistance
- Function calling
Limits
- Requires large VRAM for high‑quality quants
- No vision support
- License is other (not open source)
Best for
- Developers needing code generation
- Chatbot developers
- Tool‑integrated applications
Who it’s for. Engineers and researchers who need a versatile LLM with strong coding support. The model is suitable for local deployment on systems with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 52.7 GB (2 parts) | 93.4 GB | Too big | Get file → | |
| IQ2_XXS | 61.5 GB (2 parts) | 102.3 GB | Too big | Get file → | |
| IQ2_XS | 68.7 GB (2 parts) | 109.5 GB | Too big | Get file → | |
| IQ2_M | 76.9 GB (2 parts) | 117.7 GB | Too big | Get file → | |
| Q2_K | 85.9 GB (3 parts) | 126.7 GB | Too big | Get file → | |
| Q2_K_L | 86.5 GB (3 parts) | 127.2 GB | Too big | Get file → | |
| IQ3_XXS | 90.8 GB (3 parts) | 131.6 GB | Too big | Get file → | |
| Q3_K_S | 101.7 GB (3 parts) | 142.4 GB | Too big | Get file → | |
| IQ3_M | 103.4 GB (3 parts) | 144.1 GB | Too big | Get file → | |
| Q3_K_L | 122.4 GB (4 parts) | 163.1 GB | Too big | Get file → | |
| Q3_K_XL | 122.8 GB (4 parts) | 163.6 GB | Too big | Get file → | |
| IQ4_XS | 125.6 GB (4 parts) | 166.3 GB | Too big | Get file → | |
| Q4_0 | 133.4 GB (4 parts) | 174.2 GB | Too big | Get file → | |
| Q4_K_M | 142.5 GB (4 parts) | 183.2 GB | Too big | Get file → | |
| Q5_K_M | 167.2 GB (5 parts) | 208.0 GB | Too big | Get file → | |
| Q6_K | 193.5 GB (5 parts) | 234.3 GB | Too big | Get file → | |
| Q8_0 | 250.6 GB (7 parts) | 291.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (file size 52.68 GB, estimated 93.4 GB memory). For 16 GB VRAM, IQ2_XXS (61.5 GB, 102.3 GB). For 24 GB VRAM, IQ2_XS (68.71 GB, 109.5 GB). Higher quants such as Q4_K_M or Q5_K_M require 32 GB or more.
What GPU do you need for DeepSeek V2.5?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which DeepSeek V2.5 quant should you choose?
Q4_K_M is the usual starting point for DeepSeek V2.5: it balances file size and quality well. Here it is a 142.5 GB file.
The Q8_0 file is 250.6 GB, about 1.8 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.
If memory is tight, the smallest file is IQ1_M at 52.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V2.5
How much VRAM does DeepSeek V2.5 need?
About 183.2 GB at Q4_K_M with an 8K context window. That is the 142.5 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 DeepSeek V2.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 93.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V2.5 GGUF?
It depends on the quant: IQ1_M is 52.7 GB, IQ2_XXS is 61.5 GB, IQ2_XS is 68.7 GB, IQ2_M is 76.9 GB, Q2_K is 85.9 GB, Q2_K_L is 86.5 GB and 11 more.
What context length does DeepSeek V2.5 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 40.3 GB at 8K and 161.1 GB at 32K.
Where can I download DeepSeek V2.5 GGUF?
The files are on Hugging Face in the bartowski/DeepSeek-V2.5-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 DeepSeek V2.5 use?
Hugging Face lists the license as other. 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 DeepSeek V2.5 on 8 GB VRAM?
Use the IQ1_M quant; it requires about 93.4 GB of memory at 8k context, which is beyond 8 GB VRAM, so it will not fit entirely on the GPU. You would need to use CPU or a larger GPU.
Does DeepSeek V2.5 support vision tasks?
No, the model does not include vision capabilities.
What is the maximum context length for DeepSeek V2.5?
The model was trained with a context length of 163,840 tokens.