whatmodel.sh / DeepSeek-Coder 7B Base v1.5

DeepSeek-Coder 7B Base v1.5

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

DeepSeek-Coder 7B Base v1.5 is an open-weights language model from DeepSeek, released January 2024. Its published size is 6.91B parameters. Licence: deepseek.

Catalogue identity notes

Comparison-only. Maker repo deepseek-ai/deepseek-coder-7b-base-v1.5 @98f0904: licence tag other (deepseek-license). 6,910,365,696 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-01: month the maker's Hugging Face repo was created (createdAt 2024-01-25). DeepSeek-Coder v1.5 base (continued pretraining from DeepSeek-LLM 7B).

38.5±1.2#739 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of DeepSeek-Coder 7B Base v1.5, out of 1132 with a score, then more from DeepSeek.

#modelscorewhereRAMreleased
901Llama 2 70B Chat Meta39±1local~32GB2023-07
902Code Llama 13B Instruct Meta39±1local~9.8GB2023-08
903DeepSeek-Coder 7B Base v1.5 DeepSeek39±1local~5.9GB2024-01
904MistralHermes-CodePro-7B-v1 beowolx39±1local~6.1GB2023-12
905Llama-3-Instruct-8B-SimPO-v0.2 Princeton NLP39±1local~6.6GB2024-07
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▁▁▁▃▆██▇▆▄▃▁ #403 of 469 * · 66% of its score · 1 test

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval42.1% ✎▁█▄▅▇█·▄▇▅▄▄ beats 13/42easy · avg 78%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 66%sharp · at its level
other tests1 not in a task · 34% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)33.0% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 20/42medium · avg 55%▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%at its level

$ 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-Coder 7B Base v1.5 · needs ~4.2 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/deepseek-coder-7b-base-v1.5-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/deepseek-coder-7b-base-v1.5-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-Coder 7B Base v1.5 · needs ~4.2 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/deepseek-coder-7b-base-v1.5-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run DeepSeek-Coder 7B Base v1.5 · needs ~4.2 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/deepseek-coder-7b-base-v1.5-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~13.82 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-coder-7b-base-v1.5', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

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

$ how the score was worked out · Top Leaderboard Ranking = Top… 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
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 38.5

$ 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