whatmodel.sh / Command R (08-2024)
Command R (08-2024)
↗ share
+ contribute
Command R (08-2024) is an open-weights language model from Cohere, released August 2024. Its published size is 32.3B parameters and a 128k-token context window. Licence: cc-by-nc-4.0.
Catalogue identity notes
Arena entry 'command-r-08-2024' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'command-r-08-2024' as 'Command R (08-2024)' (Cohere, CC-BY-NC-4.0), linking https://docs.cohere.com/docs/command-r-plus#model-details. Maker repo CohereLabs/c4ai-command-r-08-2024 @dc835b8: licence tag cc-by-nc-4.0. 32,296,476,672 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-08: month the maker's Hugging Face repo was created (createdAt 2024-08-19). Cohere models page lists command-r-08-2024 as Live.
$ how it compares
The LLMs ranked either side of Command R (08-2024), out of 828 with a score, then more from Cohere.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 499 |  Llama 3 70B (base) | 46±2 | local | ||
| 500 |  Granite 4.0 Micro 3B | 46±1 | local | ||
| 501 | Command R (08-2024) | 46±1 | api $0.26/M +local | ||
| 502 |  GPT-3.5 Turbo (0301) | 46±1 | comparison only | ||
| 503 |  Nova Micro | 46±2 | api $0.061/M | ||
| more from Cohere | |||||
| 76 | North Small Translate 1.0 | 71±6 | api price unknown | ||
| 175 | Command A+ (05-2026) | 64±1 | api price unknown +local | ||
| 277 | Command A (03-2025) | 57±1 | api $4.38/M +local | ||
$ what it's good at
agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #281 of 300 * · 5.7% of its score · 1 test
Beats GLM-4 9B Chat here, though they rank higher overall. Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| SWE-bench Verified lab | 11.6% ✎ | ▃···▃·▃·▃█·▃ beats 1/7 | 5.7% |
coding▁▁▁▃▆██▇▆▄▃▁ #336 of 458 · 37% of its score · 6 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.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Aider code editing (133 Exercism Python exercises, two attempts) | 38.3% ✎ | ▁·▁▂▄▁▆▄█▆▂▂ beats 9/62 | 16% |
| SWE-bench Verified lab | 11.6% ✎ | ▃···▃·▃·▃█·▃ beats 1/7 | 5.7% |
| MBPP+ lab | 74.3% ✎ | ██·██···████ beats 1/7 | 5.3% |
| LiveCodeBench v5 (Oct 2024–Feb 2025) lab | 11.0% ✎ | ▄▄·▄·····█▄█ beats 1/7 | 4.2% |
| BIRD-SQL (dev) lab | 47.3% ✎ | ▄··▄·▄·█··▄█ beats 1/7 | 3.1% |
| Aider polyglot (225 exercises, two attempts) lab | 1.8% ✎ | █▄··█·█····▄ beats 0/7 | 2.6% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #275 of 393 * · 8.3% of its score · 1 test
Beats Ministral 3 14B Reasoning 2512, Ministral 3 14B, Gemma 4 E4B here, though they rank higher overall. Trails Flan-T5 XXL, EXAONE 3.5 2.4B Instruct, LFM2 1.2B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1250.4 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 92/379 | 8.3% |
other tests9 not in a task · 55% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LiveBench 2024-07-26 | 30.8% ✎ | ▁▁▁▂▂▃▂█▆▃▅▃ beats 29/61 | 33% |
| RepoQA (32K, threshold 0.8) lab | 73.2% ✎ | ▄▄▄··▄▄··▄·█ beats 1/7 | 8.0% |
| Open Persian LLM Leaderboard v2 average (21 tasks) | 59.8% ✎ | ▂▄▂▃█▄▃▆▃▅▂▂ beats 49/81 | 3.6% |
| BigCodeBench (Instruct) lab | 34.3% ✎ | ▄··▄▄···▄▄█▄ beats 2/7 | 3.6% |
| RULER 64k | 86.6% ✎ | ▁▁·▁·▂▃▄█▂·▁ beats 18/22 | 2.1% |
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 74.4% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 218/276 | 1.9% |
| EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy | 88.2% ✎ | ▁▁▁▁▁▁▁▂▄█▄▃ beats 109/146 | 1.1% |
| RULER 128k | 74.7% ✎ | ▄··▂▄▂▆██▄▄▂ beats 13/21 | 0.8% |
1 more test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 95.1% ✎ | ▁▁▂▃▄▄█▆▃▂▂▁ beats 60/140 | 0.6% |
$ where to run it
Through an API
api · $0.26/M · $0.15 in / $0.6 out per 1M tokens · 128k context · docs.cohere.com ↗ · price sourceUSD per 1M text tokens, standard input and output (LiteLLM @c19ce71 row 'command-r-08-2024', litellm_provider cohere_chat). Product: Cohere Chat API. API model: command-r-08-2024 (Cohere models page: Live). Currency: USD.
llama.cpp · recommended
version
- 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 | shWindowsirm https://llama.app/install.ps1 | iex - Run Command R (08-2024) · needs ~19.8 GB · from huggingface.co/lmstudio-communitychat in the terminal
llama cli -hf lmstudio-community/c4ai-command-r-08-2024-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf lmstudio-community/c4ai-command-r-08-2024-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Command R (08-2024) · needs ~19.8 GB · from huggingface.co/lmstudio-community
- Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/c4ai-command-r-08-2024-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Command R (08-2024) · needs ~19.88 GB · from ollama.comchat in the terminal
ollama run command-r:35b-08-2024-q4_K_M
MLX (Mac)
version
- Install MLX (Mac) · Apple silicon Macs only, text only.with uv
uv tool install mlx-lmorpip install mlx-lm - Run Command R (08-2024) · needs ~18.2 GB, Mac only · from huggingface.co/mlx-communitychat in the terminal
mlx_lm.chat --model mlx-community/c4ai-command-r-08-2024-4bit - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/c4ai-command-r-08-2024-4bit
Weights and documentation: huggingface.co/CohereLabs ↗
$ how the score was worked out · LiveBench model judgments (HF… 33%, Cohere — Command A technical… 32%, Aider code editing benchmark… 16% and 6 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
| source | results | share of the score |
|---|---|---|
 LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets | 1 | 33% |
 Cohere — Command A technical report · lab-reported | 7 | 32% |
 Aider code editing benchmark runs (old edit leaderboard) | 1 | 16% |
 LMArena leaderboard dataset | 1 | 8% |
| Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab) | 1 | 4% |
| NVIDIA RULER repository README results table | 2 | 3% |
| Open Portuguese LLM Leaderboard (archived) | 1 | 2% |
| EuroEval leaderboards (results collection), English generative leaderboard | 1 | 1% |
| Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 1% |
| prior · pull toward the middle | 0% | |
| weighted average | = 46.0 |
$ improve this page
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