whatmodel.sh / speechless-codellama-34b-v2.0

speechless-codellama-34b-v2.0

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

speechless-codellama-34b-v2.0 is an open-weights language model from uukuguy, released October 2023. Licence: llama2.

Catalogue identity notes

Maker repo uukuguy/speechless-codellama-34b-v2.0 @419bc42: licence tag llama2. Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-04).

48.9±0.9#364 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of speechless-codellama-34b-v2.0, out of 828 with a score, then more from uukuguy.

#modelscorewhereRAMreleased
433LFM2.5 1.2B Thinking Liquid AI49±2local~2.2GB2026-01
434Qwen3-VL 2B Thinking Alibaba49±1local~2.7GB2025-10
435speechless-codellama-34b-v2.0 uukuguy49±1local~23GB2023-10
436Pixtral 12B (2409) Mistral49±2local~9.6GB2024-09
437Nova Lite Amazon49±2api $0.10/M2024-12
more from uukuguy
480speechless-coder-ds-6.7b uukuguy47±1local~5.8GB2023-12
523speechless-starcoder2-15b uukuguy45±1local~12GB2024-03
596speechless-starcoder2-7b uukuguy42±1local~6.1GB2024-03

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #271 of 458 · 100% of its score · 3 tests

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, Mistral NeMo Instruct (2407), QwQ-32B-Preview here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval77.4% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 79/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%sharp
HumanEval+72.0% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 77/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%sharp · at its level
MBPP+61.4% ✎▁···▁▁▂▅▇█▆▂ beats 39/75easy · avg 68%▇▇▇ 8.1%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 speechless-codellama-34b-v2.0 · needs ~20.2 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/speechless-codellama-34b-v2.0-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/speechless-codellama-34b-v2.0-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 speechless-codellama-34b-v2.0 · needs ~20.2 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-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 speechless-codellama-34b-v2.0 · needs ~20.2 GB · from huggingface.co/TheBloke
    chat in the terminal
    ollama run hf.co/TheBloke/speechless-codellama-34b-v2.0-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~67.49 GB · from huggingface.co/uukuguy (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='uukuguy/speechless-codellama-34b-v2.0', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/uukuguy ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 100%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 48.9

$ 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