whatmodel.sh / DeepSeek-V2 Chat (0628)

DeepSeek-V2 Chat (0628)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

DeepSeek-V2 Chat (0628) is an open-weights language model from DeepSeek, released July 2024. Its published size is 235.74B parameters (21B active per token). Licence: other (deepseek).

Catalogue identity notes

Maker repo deepseek-ai/DeepSeek-V2-Chat-0628 @5d09e27: licence tag other (deepseek). 235,741,434,880 parameters from the Hugging Face safetensors metadata; active 21B per token (DeepSeek-V2 architecture: 236B total, 21B activated per token (DeepSeek-V2 card/report)). Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-18). DeepSeek API updates page (api-docs.deepseek.com/updates): 'Date: 2024-06-28 deepseek-chat: The deepseek-chat model has been upgraded to DeepSeek-V2-0628' (replaced by DeepSeek-V2.5 on 2024-09-05). Distinct from the catalogued DeepSeek-V2.5 / V2.5-1210 and V2-Lite.

53.5±1.0#291 of 719 LLMsfrom 6 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of DeepSeek-V2 Chat (0628), out of 828 with a score, then more from DeepSeek.

#modelscorewhereRAMreleased
346Llama 3.1 Tulu 3 70B Ai254±1local~43GB2024-11
347DeepSeek-V2.5 DeepSeek54±1local~151GB2024-09
348DeepSeek-V2 Chat (0628) DeepSeek54±1local~66GB2024-07
349GLM-4 9B Chat 1M Zhipu AI (THUDM)53±5local~8.1GB2024-06
350Mistral Small 3 24B (2501) Mistral53±1local~16GB2025-01
more from DeepSeek
21DeepSeek V4.1 Flash DeepSeek78±1api $0.26/M +local~537GB2026-09
31DeepSeek V4 Pro (0813) DeepSeek76±1api $1.63/M +local~1010GB2026-08
35DeepSeek V3.2 Speciale DeepSeek76±3comparison only

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #199 of 458 * · 35% of its score · 2 tests

Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Falcon-H1R 7B here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 3B Reasoning 2512, DeepSeek-Coder-V2 Instruct (0724) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
CRUXEval (ZeroEval, 800 problems)70.5% ✎▁▂▆▃▆█▆▃▂·▁▁ beats 31/47medium · avg 61%▇▇▇▇▇▇▇▇ 20%sharp · at its level
Aider code editing (133 Exercism Python exercises, two attempts)69.9% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 48/62medium · avg 54%▇▇▇▇▇▇ 15%at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #260 of 398 * · 6.7% of its score · 1 test

Beats Molmo 2 8B, Llama 3.3 70B Instruct, DeepSeek-V2.5 here, though they rank higher overall. Trails DeepSeek R1 Distill Qwen 1.5B, Mixtral 8x7B v0.1 (base), Tulu 2 DPO 70B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K (ZeroEval, zero-shot)93.9% ✎▁▄·▁▄█▅▅▅███ beats 31/43very easy · avg 89%▇▇▇ 6.7%sharp · maxed out
other tests3 not in a task · 58% of its score
testresultvs the others in its rundifficultycountswhy
MMLU-Redux (ZeroEval, 2,778 questions)80.8% ✎▁·▁▁▄▄▄▅█▄▂▁ beats 30/53easy · avg 77%▇▇▇▇▇▇▇▇▇▇▇▇▇ 31%typical
ZebraLogic (ZeroEval, 1,000 puzzles)22.7% ✎▁▁▃▆██▁▁·▁▁▁ beats 35/57hard · avg 18%▇▇▇▇▇▇▇ 17%sharp · at its level
WildBench v2 WB-Score (task macro)53.9943 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 45/52avg 45.199 WB-Score▇▇▇▇ 9.4%sharp

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run DeepSeek-V2 Chat (0628) · needs ~142.5 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/DeepSeek-V2-Chat-0628-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/DeepSeek-V2-Chat-0628-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run DeepSeek-V2 Chat (0628) · needs ~142.5 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/DeepSeek-V2-Chat-0628-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Other ways to run it

  1. Run it as published · needs ~471.49 GB · from huggingface.co/deepseek-ai
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='deepseek-ai/DeepSeek-V2-Chat-0628', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/deepseek-ai ↗

$ how the score was worked out · WildEval ZeroEval published r… 75%, Aider code editing benchmark… 15%, WildBench v2 leaderboard data… 9%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
WildEval ZeroEval published results4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 75%Apache-2.0
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇▇▇ 15%Apache-2.0
WildBench v2 leaderboard data (Ai2)1▇▇▇ 9%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 53.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json