LLMs · DeepSeek

DeepSeek V2 Chat

Name: DeepSeek V2 Chat
Author: DeepSeek

Parameters: 236B (21.0B active)
Architecture: Mixture of experts
Max context: 160K tokens
License: deepseek
Released: 2024-04

How to run it

Quickest · Ollama

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

ollama run deepseek-v2:236b

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-V2-Chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/DeepSeek-V2-Chat-i1-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-V2-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.

KV cache: latent (MLA) KV cache.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	94.3 GB	95.5 GB	97.2 GB
`Q3_K_M`	Low	116 GB	117 GB	118 GB
`Q4_K_M`	Good	144 GB	145 GB	147 GB
`Q5_K_M`	High	167 GB	169 GB	170 GB
`Q6_K`	High	193 GB	194 GB	196 GB
`Q8_0`	Very high	250 GB	251 GB	253 GB
`F16`	Full	471 GB	473 GB	474 GB	Original weights (opens in a new tab)

Best hardware for DeepSeek V2 Chat

Grade · points	Hardware	Quant	Memory	Speed	Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15	Apple M3 Ultra (256 GB)	`Q4_K_M`	160 GB / 192 GB	20.6 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 23.4/45, Memory fit 24.0/25, Speed 12.1/15, Memory use 15.0/15	Apple M2 Ultra (192 GB)	`Q3_K_M`	128 GB / 144 GB	26.0 tok/s	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 10.6/15	Apple M3 Ultra (512 GB)	`Q4_K_M`	176 GB / 384 GB	20.6 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 19.5/45, Memory fit 24.0/25, Speed 8.6/15, Memory use 15.0/15	NVIDIA GB10 (128 GB)	`Q2_K`	105 GB / 115 GB	13.1 tok/s	Tight fit
59 ptsGood (B) · 59 of 100 points: Model quality 19.5/45, Memory fit 10.0/25, Speed 14.9/15, Memory use 15.0/15	NVIDIA RTX PRO 6000 Blackwell	`Q2_K`	100 GB / 96.0 GB	39.6 tok/s	Runs with offload
54 ptsUsable (C) · 54 of 100 points: Model quality 19.5/45, Memory fit 10.0/25, Speed 10.4/15, Memory use 15.0/15	Apple M4 Max (128 GB)	`Q2_K`	103 GB / 96.0 GB	19.2 tok/s	Runs with offload
51 ptsUsable (C) · 51 of 100 points: Model quality 19.5/45, Memory fit 10.0/25, Speed 7.1/15, Memory use 15.0/15	AMD Ryzen AI Max+ 395 (128 GB)	`Q2_K`	103 GB / 96.0 GB	9.0 tok/s	Runs with offload

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.