whatmodel.sh / Command R7B (12-2024)

Command R7B (12-2024)

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

Command R7B (12-2024) is an open-weights language model from Cohere, released December 2024. Its published size is 8.03B parameters and a 128k-token context window. Licence: cc-by-nc-4.0.

Catalogue identity notes

Maker repo CohereLabs/c4ai-command-r7b-12-2024 @4f3d0aa: licence tag cc-by-nc-4.0. 8,028,033,024 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-12: month the maker's Hugging Face repo was created (createdAt 2024-12-11). Smallest Command R-series model (December 2024), not Command R 03-2024/08-2024 or the Arabic 02-2025 variant. Ollama tags command-r7b:7b-12-2024-q4_K_M / -q8_0 are the library's builds of this checkpoint (tag names on the tags page); sizes estimated from the parameter count. Evaluated in this lane's sources as 'CohereForAI/c4ai-command-r7b-12-2024', 'Command R7B (FC)', 'c4ai-command-r7b-12-2024'.

44.2±1.3#453 of 719 LLMsfrom 14 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Command R7B (12-2024), out of 828 with a score, then more from Cohere.

#modelscorewhereRAMreleased
540Phi-3-mini-4k-instruct (June 2024 update) Microsoft44±1local~3.7GB2024-06
541Yi 1.5 9B Chat 01.AI44±1local~6.8GB2024-05
542Command R7B (12-2024) Cohere44±1local~6.2GB2024-12
543Qwen2-Audio 7B Instruct Alibaba44±3local~6.5GB2024-07
544Gemma 3 4B Google44±1api $0.063/M +local~3.8GB2025-03
more from Cohere
76North Small Translate 1.0 Cohere71±6api price unknown2026-08
175Command A+ (05-2026) Cohere64±1api price unknown +local~71GB2026-05
277Command A (03-2025) Cohere57±1api $4.38/M +local~37GB2025-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #248 of 300 · 18% of its score · 3 tests

Beats DeepSeek R1 0528 Qwen3 8B, Magistral Small 1.0 (2506), Llama 4 Scout (109B-A17B) here, though they rank higher overall. Trails Granite 4.0 H 1B, Granite 4.0 1B, SmolLM3 3B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Verified lab3.6% ✎▃···▃·▃·▃█·▃ beats 0/7hard · avg 19%▇▇▇▇ 9.0%sharp
BFCL V4 (December 2025 archive)32.1% ✎▁▁▁▂██▅▅▆▂▂▂ beats 35/77hard · avg 32%▇▇ 5.7%typical
BFCL v351.7% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 42/114medium · avg 52%▇ 3.4%blunt · at its level
coding▁▁▁▃▆██▇▆▄▃▁ #363 of 458 · 35% of its score · 5 tests

Beats LFM2.5 8B-A1B, Qwen3-VL 2B Thinking, DeepSeek R1 Distill Qwen 7B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, Phi-3-mini-128k-instruct (Apr 2024), OpenHermes 2.5 Mistral 7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MBPP+ lab72.0% ✎██·██···████ beats 0/7easy · avg 79%▇▇▇▇ 10%at its level
SWE-bench Verified lab3.6% ✎▃···▃·▃·▃█·▃ beats 0/7hard · avg 19%▇▇▇▇ 9.0%sharp
LiveCodeBench v5 (Oct 2024–Feb 2025) lab9.0% ✎▄▄·▄·····█▄█ beats 0/7hard · avg 19%▇▇▇ 6.9%typical
BIRD-SQL (dev) lab42.2% ✎▄··▄·▄·█··▄█ beats 0/7medium · avg 49%▇▇ 5.6%at its level
Aider polyglot (225 exercises, two attempts) lab2.7% ✎█▄··█·█····▄ beats 2/7very hard · avg 6.7%▇ 3.4%sharp · too hard for it · noisy
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #223 of 393 * · 12% of its score · 2 tests

Beats Granite 4.2 8B, Mistral Small 4 (119B-A6.5B), Olmo 3.1 32B Think here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Gemma 3 4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arabic IFEval prompt-level (Inception)56.4% ✎▁·▁▁▂▁▄▄▆▄█▄ beats 30/38medium · avg 49%▇▇▇▇▇ 12%sharp · at its level
IFEval strict, mean of prompt and instruction level lab77.9% ✎█··········█ beats 0/1—not counted yet: no other model in the same run to compare it with
other tests7 not in a task · 43% of its score
testresultvs the others in its rundifficultycountswhy
RepoQA (32K, threshold 0.8) lab69.6% ✎▄▄▄··▄▄··▄·█ beats 0/7easy · avg 81%▇▇▇▇▇▇ 16%at its level
Open Persian LLM Leaderboard v2 average (21 tasks)50.4% ✎▂▄▂▃█▄▃▆▃▅▂▂ beats 30/81medium · avg 58%▇▇▇ 6.7%blunt · at its level
BigCodeBench (Instruct) lab30.9% ✎▄··▄▄···▄▄█▄ beats 1/7medium · avg 36%▇▇▇ 6.4%at its level
MMLU-Pro lab42.4% ✎▁▁·▁▁▁▃▂▄▅█▁ beats 33/188medium · avg 56%▇▇▇ 6.3%at its level · small run
GPQA Diamond (simple-evals) lab26.3% ✎▃·····▄█▂▂▃▃ beats 0/22hard · avg 36%▇▇ 5.4%sharp · too hard for it · small run
MMLU (simple-evals, zero-shot CoT) lab65.2% ✎▃···▂▁▅█▂▂▃▁ beats 0/22easy · avg 78%▇ 3.1%at its level · small run
InFoBench lab85.6% ✎█··········█ beats 0/1—not counted yet: no other model in the same run to compare it with

$ 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 Command R7B (12-2024) · needs ~5.1 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/c4ai-command-r7b-12-2024-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/c4ai-command-r7b-12-2024-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 Command R7B (12-2024) · needs ~5.1 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/c4ai-command-r7b-12-2024-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 Command R7B (12-2024) · needs ~5.32 GB · from ollama.com
    chat in the terminal
    ollama run command-r7b:7b-12-2024-q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Command R7B (12-2024) · needs ~4.5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/c4ai-command-r7b-12-2024-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/c4ai-command-r7b-12-2024-4bit

Weights and documentation: huggingface.co/CohereLabs ↗

$ how the score was worked out · Cohere — Command A technical… 72%, Inception Arabic/Hindi leader… 12%, Berkeley Function Calling Lea… 9% and 1 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
Cohere — Command A technical report · lab-reported10▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 72%CC BY 4.0
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)1▇▇▇▇ 12%Apache-2.0
Berkeley Function Calling Leaderboard result archive2▇▇▇ 9%Apache-2.0
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)1▇▇ 7%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 44.2

not counted (2)

Cohere — Command A technical reportIFEval strict, mean of prompt and instruction level [correct]77.9%fewer than three models have this test yet, or this source ran it for this model alone
Cohere — Command A technical reportInFoBench [correct]85.6%fewer than three models have this test yet, or this source ran it for this model alone

$ 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