DeepSeek R1 0528 needs about 410.8 GB of memory at Q4_K_M (a 409.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 147.4 GB (IQ1_M) to 713.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
DeepSeek R1 0528 – 670B parameter model focused on reasoning
DeepSeek R1 0528 is a 670 billion‑parameter model in the DeepSeek family, built on the deepseek2 architecture. It is a mixture of experts and was trained on 163 840 context tokens. The model is released under the MIT license and supports advanced reasoning tasks.
Good at
- Advanced reasoning
- Complex problem solving
- Function calling
Limits
- Requires large VRAM for full precision
- No vision support
- No explicit language list
Best for
- Academic research on reasoning models
- Industrial development of small‑scale reasoning tools
- Benchmarking open‑source models
Who it’s for. Researchers and developers needing a high‑capacity reasoning model. The model is suitable for users who can allocate sufficient GPU memory and are comfortable with GGUF and llama.cpp tooling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 147.4 GB (4 parts) | 149.0 GB | Too big | Get file → | |
| IQ2_XXS | 164.1 GB (5 parts) | 165.6 GB | Too big | Get file → | |
| IQ2_XS | 188.4 GB (5 parts) | 190.0 GB | Too big | Get file → | |
| IQ2_S | 189.6 GB (5 parts) | 191.2 GB | Too big | Get file → | |
| IQ2_M | 215.0 GB (6 parts) | 216.6 GB | Too big | Get file → | |
| Q2_K | 237.8 GB (7 parts) | 239.4 GB | Too big | Get file → | |
| Q2_K_L | 238.7 GB (7 parts) | 240.3 GB | Too big | Get file → | |
| IQ3_XXS | 267.6 GB (7 parts) | 269.2 GB | Too big | Get file → | |
| IQ3_XS | 277.1 GB (8 parts) | 278.7 GB | Too big | Get file → | |
| Q3_K_S | 293.4 GB (8 parts) | 294.9 GB | Too big | Get file → | |
| IQ3_M | 307.9 GB (8 parts) | 309.5 GB | Too big | Get file → | |
| Q3_K_M | 307.9 GB (8 parts) | 309.5 GB | Too big | Get file → | |
| Q3_K_L | 319.7 GB (9 parts) | 321.3 GB | Too big | Get file → | |
| Q3_K_XL | 320.5 GB (9 parts) | 322.1 GB | Too big | Get file → | |
| IQ4_XS | 360.0 GB (10 parts) | 361.6 GB | Too big | Get file → | |
| IQ4_NL | 380.5 GB (10 parts) | 382.1 GB | Too big | Get file → | |
| Q4_0 | 386.4 GB (10 parts) | 388.0 GB | Too big | Get file → | |
| Q4_K_S | 394.2 GB (11 parts) | 395.7 GB | Too big | Get file → | |
| Q4_K_M | 409.2 GB (11 parts) | 410.8 GB | Too big | Get file → | |
| Q4_1 | 421.0 GB (11 parts) | 422.6 GB | Too big | Get file → | |
| Q5_K_S | 463.0 GB (12 parts) | 464.6 GB | Too big | Get file → | |
| Q5_K_M | 478.3 GB (13 parts) | 479.9 GB | Too big | Get file → | |
| Q6_K | 552.4 GB (15 parts) | 554.0 GB | Too big | Get file → | |
| Q8_0 | 713.3 GB (20 parts) | 714.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (149 GB memory at 8 k context) or IQ2_XXS (165.6 GB). For 16 GB VRAM, IQ2_XS (190 GB) or IQ2_S (191.2 GB) are suitable. For 32 GB VRAM, IQ3_K_S (294.9 GB) or IQ3_K_M (309.5 GB) provide a balance of size and quality. Memory estimates are approximate.
What GPU do you need for DeepSeek R1 0528?
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 R1 0528 quant should you choose?
Q4_K_M is the usual starting point for DeepSeek R1 0528: it balances file size and quality well. Here it is a 409.2 GB file.
The Q8_0 file is 713.3 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.
If memory is tight, the smallest file is IQ1_M at 147.4 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 R1 0528
How much VRAM does DeepSeek R1 0528 need?
About 410.8 GB at Q4_K_M with an 8K context window. That is the 409.2 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 0528 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 149.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek R1 0528 GGUF?
It depends on the quant: IQ1_M is 147.4 GB, IQ2_XXS is 164.1 GB, IQ2_XS is 188.4 GB, IQ2_S is 189.6 GB, IQ2_M is 215.0 GB, Q2_K is 237.8 GB and 18 more.
What context length does DeepSeek R1 0528 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download DeepSeek R1 0528 GGUF?
The files are on Hugging Face in the bartowski/deepseek-ai_DeepSeek-R1-0528-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 R1 0528 use?
Hugging Face lists the license as mit. 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 R1 0528 on 8 GB VRAM?
Only the smallest quantizations such as IQ1_M or IQ2_XXS can fit, but they will still require around 150–165 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision tasks?
No, the model is text‑only and does not include vision capabilities.
What license does the model use?
The model is released under the MIT license, allowing free use and modification.