DE

DeepSeek-R1-Distill-Llama-70B

DeepSeekGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant18.2 GB
Quick answer

DeepSeek-R1-Distill-Llama-70B needs about 46.0 GB of memory at Q4_K_M (a 42.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 30 quants, from 18.2 GB (IQ1_S) to 141.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

DeepSeek-R1-Distill-Llama-70B – 70.6B parameter Llama model

DeepSeek-R1-Distill-Llama-70B is a 70.6B parameter Llama architecture model. It supports reasoning and tool use. The model is released under the MIT license.

Good at

  • Reasoning
  • Tool usage
  • Large context support

Limits

  • No vision support
  • Large memory requirement
  • No mixture of experts

Best for

  • Complex reasoning tasks
  • Tool‑integrated workflows
  • High‑capacity context applications

Who it’s for. Developers needing a large Llama model with reasoning and tool‑use capabilities. The model is suitable for applications that can accommodate its memory footprint and do not require vision or mixture‑of‑experts features.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S18.2 GB 21.4 GB
Too big Get file →
IQ1_M19.5 GB 22.7 GB
Too big Get file →
IQ2_XXS21.2 GB 24.4 GB
Too big Get file →
IQ2_XS22.7 GB 25.9 GB
Too big Get file →
Q2_K_S24.7 GB 27.9 GB
Too big Get file →
IQ2_S26.1 GB 29.2 GB
Too big Get file →
IQ2_M27.4 GB 30.6 GB
Too big Get file →
IQ3_XXS28.0 GB 31.2 GB
Too big Get file →
IQ3_XS29.7 GB 32.9 GB
Too big Get file →
Q3_K_S31.0 GB 34.2 GB
Too big Get file →
IQ3_S31.3 GB 34.5 GB
Too big Get file →
IQ3_M32.3 GB 35.5 GB
Too big Get file →
Q3_K_M34.7 GB 37.9 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q4_039.7 GB 42.9 GB
Too big Get file →
IQ4_NL40.1 GB 43.2 GB
Too big Get file →
Q4_K_S40.6 GB 43.8 GB
Too big Get file →
Q4_K_M42.8 GB 46.0 GB
Too big Get file →
Q4_144.1 GB 47.3 GB
Too big Get file →
Q5_048.5 GB 51.7 GB
Too big Get file →
Q5_K_S48.8 GB 52.0 GB
Too big Get file →
Q5_153.6 GB (2 parts) 56.8 GB
Too big Get file →
Q6_K_M57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q6_K_L58.4 GB (2 parts) 61.6 GB
Too big Get file →
BF1660.4 GB (2 parts) 63.6 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →
BF1676.9 GB (2 parts) 80.1 GB
Too big Get file →
F1676.9 GB (2 parts) 80.1 GB
Too big Get file →
BF16141.1 GB (4 parts) 144.3 GB
Too big Get file →
F16141.1 GB (4 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 18.2 GB, estimated 21.4 GB memory at 8 k context). For 16 GB VRAM, IQ1_M (19.5 GB, 22.7 GB memory). For 24 GB VRAM, Q4_K_M (42.79 GB, 46 GB memory).

What GPU do you need for DeepSeek-R1-Distill-Llama-70B?

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: the best quant that fits is IQ1_M (19.5 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (28.0 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (44.1 GB file, about 47.3 GB in use).

Which DeepSeek-R1-Distill-Llama-70B quant should you choose?

Q4_K_M is the usual starting point for DeepSeek-R1-Distill-Llama-70B: it balances file size and quality well. Here it is a 42.8 GB file.

The Q8_0 file is 75.0 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_S at 18.2 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

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byMungert
FamilyDeepSeek
Licensemit
Downloads (HF)737
Last updated2025-09-24

Frequently asked questions about DeepSeek-R1-Distill-Llama-70B

How much VRAM does DeepSeek-R1-Distill-Llama-70B need?

About 46.0 GB at Q4_K_M with an 8K context window. That is the 42.8 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-Llama-70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek-R1-Distill-Llama-70B GGUF?

It depends on the quant: IQ1_S is 18.2 GB, IQ1_M is 19.5 GB, IQ2_XXS is 21.2 GB, IQ2_XS is 22.7 GB, Q2_K_S is 24.7 GB, IQ2_S is 26.1 GB and 24 more.

What context length does DeepSeek-R1-Distill-Llama-70B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download DeepSeek-R1-Distill-Llama-70B GGUF?

The files are on Hugging Face in the Mungert/DeepSeek-R1-Distill-Llama-70B-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-Distill-Llama-70B 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-Distill-Llama-70B on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 21.4 GB memory at 8 k context, which exceeds 8 GB VRAM.

What quantization gives the best balance of size and performance?

IQ1_M offers a moderate file size of 19.5 GB and memory of 22.7 GB at 8 k context.

Is the model compatible with llama.cpp?

Yes, all listed GGUF files are compatible with llama.cpp.

Similar models

Browse all →

More from Mungert

All by Mungert →

More DeepSeek models

All DeepSeek →

Other large models

All large models →