whatmodel.sh / DeepSeek LLM 7B Chat

DeepSeek LLM 7B Chat

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

DeepSeek LLM 7B Chat is an open-weights language model from DeepSeek, released November 2023. Its published size is 7B parameters. Licence: deepseek.

Catalogue identity notes

Comparison-only, proposed so the DeepSeek-V2-Lite-Chat card runs count. The pinned DeepSeek-V2-Lite-Chat card (@8586474) prints DeepSeek's own chat models side by side: 'DeepSeek 7B Chat (SFT)', 'DeepSeekMoE 16B Chat (SFT)' and 'DeepSeek-V2-Lite 16B Chat (SFT)' (catalogue deepseek-v2-lite-chat). Weights: https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat (sha afbda8b347ec881666061fa67447046fc5164ec8, created 2023-11-29, DeepSeek model licence); same family as the catalogued deepseek-llm-67b-chat.

34.6±1.7#605 of 719 LLMsfrom 8 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of DeepSeek LLM 7B Chat, out of 828 with a score, then more from DeepSeek.

#modelscorewhereRAMreleased
698StarCoder2 7B BigCode35±1local~6.1GB2024-02
699Granite 3.0 3B-A800M Instruct IBM35±1local~3.7GB2024-10
700DeepSeek LLM 7B Chat DeepSeek35±2local~5.7GB2023-11
701StarCoder 15.5B BigCode35±1local~11GB2023-04
702Granite 3.1 3B-A800M Instruct IBM35±2local~3.6GB2024-12
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▁▁▁▃▆██▇▆▄▃▁ #404 of 458 * · 27% of its score · 2 tests

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
HumanEval lab45.1% ✎▁▁▁▁▁▃▅▅█▃▂▁ beats 68/190easy · avg 84%▇▇▇▇▇▇▇ 18%sharp · at its level · small run
MBPP lab39.0% ✎▁▁▁▄▅█▄▅▃▁▂▁ beats 13/81easy · avg 71%▇▇▇▇ 9.0%at its level · small run
math█··········█ #2 of 2 * · 26% of its score · 2 tests
testresultvs the others in its rundifficultycountswhy
GSM8K lab62.6% ✎▂▂▂▅▅▆▅▇█▇▄▃ beats 59/146very easy · avg 89%▇▇▇▇▇▇ 16%sharp · at its level · small run
MATH lab14.7% ✎▃▅▂▆▅▃▅▃█▃▃▂ beats 12/29medium · avg 47%▇▇▇▇ 10%small run
other tests4 not in a task · 45% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab43.1% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 30/129easy · avg 75%▇▇▇▇▇▇▇ 17%sharp · small run
MMLU lab49.7% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 35/183easy · avg 77%▇▇▇▇▇ 12%at its level · small run
C-Eval lab44.7% ✎▁···▁▁▃▁▂▂▃█ beats 4/33easy · avg 74%▇▇▇▇ 8.8%at its level · small run
CMMLU lab51.2% ✎▅·▅····█▃▅█▅ beats 0/14easy · avg 76%▇▇▇ 7.9%at its level · small run

$ where to run it

Ollama · recommended

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run DeepSeek LLM 7B Chat · needs ~4 GB · from ollama.com
    chat in the terminal
    ollama run deepseek-llm:7b
$ how the score was worked out · DeepSeek vendor-reported benc… 99%

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
DeepSeek vendor-reported benchmark scores for its own models (Hugging Face model cards) · lab-reported8▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Factual vendor-reported score (not licensed content)
prior · pull toward the middle▇ 1%
weighted average= 34.6

$ 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