whatmodel.sh / DeepSeek-Coder 1.3B Instruct

DeepSeek-Coder 1.3B Instruct

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

DeepSeek-Coder 1.3B Instruct is an open-weights language model from DeepSeek, released October 2023. Its published size is 1.35B parameters and a 16k-token context window. Licence: deepseek.

Catalogue identity notes

Maker repo deepseek-ai/deepseek-coder-1.3b-instruct @e063262: licence tag other (deepseek). 1,346,471,936 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-29). DeepSeek-Coder v1 instruct model. Ollama tags deepseek-coder:1.3b-instruct-q4_K_M, deepseek-coder:1.3b-instruct-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

42.6±0.6#491 of 719 LLMsfrom 14 benchmark results across 6 sources

$ how it compares

The LLMs ranked either side of DeepSeek-Coder 1.3B Instruct, out of 828 with a score, then more from DeepSeek.

#modelscorewhereRAMreleased
579Llama 3.2 11B Vision Instruct Meta43±2local~8.8GB2024-09
580Qwen2.5 3B Instruct Alibaba43±1local~3.3GB2024-09
581DeepSeek-Coder 1.3B Instruct DeepSeek43±1local~2.4GB2023-10
582Aya 23 8B Cohere For AI43±3local~6.2GB2024-05
583Phi-3-small-8k-instruct Microsoft43±2local~17GB2024-05
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▁▁▁▃▆██▇▆▄▃▁ #337 of 458 · 83% of its score · 10 tests

Beats GLM-4.7-Flash, LFM2.5 2.6B, LFM2.5 8B-A1B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +165.9% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 51/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%sharp · at its level · several runs
HumanEval+60.4% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 53/99easy · avg 74%▇▇▇▇▇▇▇▇▇ 23%sharp · at its level
LiveCodeBench official (Jan 1–Nov 1, 2024)6.5% ✎▁▃·▁▂▄▆█▅▂·▂ beats 1/31hard · avg 26%▇▇ 4.3%sharp
MBPP+54.8% ✎▁···▁▁▂▅▇█▆▂ beats 28/75easy · avg 68%▇▇ 4.0%at its level
CRUXEval-I27.2% ✎▁··▃▅▂█▇▁··▁ beats 1/22medium · avg 54%▇ 1.3%at its level
CRUXEval-O28.7% ✎▁·▃▃▁█▁▂···▁ beats 1/22medium · avg 53%▇ 1.3%blunt · at its level
CodeReviewQA: solution identification (hard), invariant accuracy0.0% ✎▃··▁▂▂▃▂█▃▄▂ beats 3/47medium · avg 54%▇ 0.8%sharp · at its level · noisy
CodeReviewQA: change localisation (hard), invariant accuracy0.0% ✎█▂▁▁▂▂▂▃▅▅▅▇ beats 4/47medium · avg 36%▇ 0.7%sharp · noisy
2 more tests
testresultvs the others in its rundifficultycountswhy
CodeReviewQA: automated code refinement, exact match rate11.7% ✎▁▁▁▁▁▃▂▂▃█▅▄ beats 7/47hard · avg 33%▇ 0.6%typical
CodeReviewQA: change type recognition, invariant accuracy1.9% ✎▁▁▃······▁▃█ beats 3/47easy · avg 67%▇ 0.0%blunt · at its level · noisy
other tests3 not in a task · 17% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)34.9% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 24/42medium · avg 55%▇▇▇▇ 10%at its level
BigCodeBench (Complete)29.3% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 10/58medium · avg 50%▇▇ 3.8%at its level
BigCodeBench (Instruct)22.7% ✎▃▂·▆▆██▆▅▃▃▃ beats 1/33medium · avg 41%▇ 3.7%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 1.3B Instruct · needs ~0.9 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/deepseek-coder-1.3b-instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/deepseek-coder-1.3b-instruct-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 1.3B Instruct · needs ~0.9 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-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 1.3B Instruct · needs ~0.874 GB · from ollama.com
    chat in the terminal
    ollama run deepseek-coder:1.3b-instruct-q4_K_M

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

$ how the score was worked out · EvalPlus / EvalPerf published… 57%, Top Leaderboard Ranking = Top… 26%, BigCodeBench paper (Zhuo et a… 7% and 3 more

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
EvalPlus / EvalPerf published evaluation runs3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇▇ 26%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v42▇▇ 7%CC BY 4.0
LiveCodeBench official website results (2024-12-26)1▇ 4%CC-BY-SA-4.0
CRUXEval published evaluation results (authors' generations and scores)2▇ 3%MIT
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇ 2%CC-BY-4.0
prior · pull toward the middle▇ 0%
weighted average= 42.6

$ 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