Check my GPU

LLMs ·

DeepSeek LLM 67B Chat

Parameters
67B
Architecture
Dense
Max context
4K tokens
License
deepseek
Released
2023-11

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run deepseek-llm:67b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/mradermacher/deepseek-llm-67b-chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/deepseek-llm-67b-chat-i1-GGUF

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/deepseek-llm-67b-chat (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 4K context Download
Q2_K Low 27.0 GB 29.2 GB GGUF (opens in a new tab)
Q3_K_M Low 33.0 GB 35.2 GB GGUF (opens in a new tab)
Q4_K_M Good 41.1 GB 43.3 GB GGUF (opens in a new tab)
Q5_K_M High 47.9 GB 50.0 GB GGUF (opens in a new tab)
Q6_K High 55.3 GB 57.5 GB GGUF files (opens in a new tab)
Q8_0 Very high 71.4 GB 73.6 GB GGUF files (opens in a new tab)
F16 Full 135 GB 137 GB Original weights (opens in a new tab)

Best hardware for DeepSeek LLM 67B Chat

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc Pro B70 (launch price $949) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
67 ptsGood (B) · 67 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 13.5/15, Memory use 11.6/15 NVIDIA RTX PRO 6000 Blackwell Q4_K_M 48.1 GB / 96.0 GB 32.6 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q2_K 30.8 GB / 32.0 GB 53.6 tok/s Tight fit
63 ptsGood (B) · 63 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q4_K_M 47.1 GB / 48.0 GB 8.6 tok/s Tight fit
62 ptsGood (B) · 62 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 5.9/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q4_K_M 47.1 GB / 48.0 GB 6.3 tok/s Tight fit
61 ptsGood (B) · 61 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 6.9/15, Memory use 12.3/15 Apple M4 Max (128 GB) Q4_K_M 51.0 GB / 96.0 GB 8.6 tok/s Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 8.8/15 Apple M2 Ultra (192 GB) Q4_K_M 54.8 GB / 144 GB 12.5 tok/s Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 12.3/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M 51.0 GB / 96.0 GB 4.0 tok/s Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 5.3/15, Memory use 10.5/15 NVIDIA GB10 (128 GB) Q4_K_M 52.5 GB / 115 GB 5.0 tok/s Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 12.6/45, Memory fit 24.0/25, Speed 6.3/15, Memory use 15.0/15 Apple M4 Pro (48 GB) Q2_K 32.0 GB / 36.0 GB 7.0 tok/s Tight fit
57 ptsUsable (C) · 57 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 7.1/15 Apple M3 Ultra (256 GB) Q4_K_M 58.7 GB / 192 GB 12.8 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.