- Size
- 111B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Creative Commons Attribution-NonCommercial 4.0Our reading, check the licence: You can use, change and share the model with credit, but not for commercial purposes.
- On the Hub since
- 11 Mar 2025the date the repo was created
- Context length
- Not known
- Kind
- Base model (no base model declared on the Hub)Cohere2ForCausalLM
- On Hugging Face
- CohereLabs/c4ai-command-a-03-20252.0k downloads in the last 30 days, 397 likes
Scores
- Edit format: whole12.0%14 Mar 2025, aider.chat
Epoch's name: c4ai-command-a-03-2025. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results
- default setting0.0%via Epoch AI
Epoch's name: c4ai-command-a-03-2025. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- default setting61.3%conceptualreasoning.ai
Epoch's name: c4ai-command-a-03-2025. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- default setting10.3%5.2 to 15.4conceptualreasoning.ai
Epoch's name: c4ai-command-a-03-2025. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.0 GB, worked out from the model's config (mlx-community/c4ai-command-a-03-2025-4bit), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF (converted by bartowski), 1.1k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 40.4 GBfile size | 42.9 GB40.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ3_XXSOllama ollama run hf.co/bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ3_XXSDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-IQ3_XXS.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| IQ3_XS | 43.3 GBfile size | 45.8 GB43.3 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ3_XSDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-IQ3_XS.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q3_K_S | 45.6 GBfile size | 48.1 GB45.6 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q3_K_SDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q3_K_S.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| IQ3_M | 47.3 GBfile size, 2 parts | 49.8 GB47.3 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ3_MDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-IQ3_M/CohereForAI_c4ai-command-a-03-2025-IQ3_M-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q3_K_M | 50.7 GBfile size, 2 parts | 53.2 GB50.7 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q3_K_MDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q3_K_M/CohereForAI_c4ai-command-a-03-2025-Q3_K_M-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q3_K_L | 55.1 GBfile size, 2 parts | 57.6 GB55.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q3_K_LDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q3_K_L/CohereForAI_c4ai-command-a-03-2025-Q3_K_L-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q3_K_XL | 55.8 GBfile size, 2 parts | 58.3 GB55.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q3_K_XLDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q3_K_XL/CohereForAI_c4ai-command-a-03-2025-Q3_K_XL-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| IQ4_XS | 55.9 GBfile size, 2 parts | 58.4 GB55.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ4_XSDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-IQ4_XS/CohereForAI_c4ai-command-a-03-2025-IQ4_XS-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| IQ4_NL | 59.0 GBfile size, 2 parts | 61.5 GB59.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:IQ4_NLDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-IQ4_NL/CohereForAI_c4ai-command-a-03-2025-IQ4_NL-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q4_0 | 59.2 GBfile size, 2 parts | 61.7 GB59.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q4_0Download hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q4_0/CohereForAI_c4ai-command-a-03-2025-Q4_0-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q4_K_S | 59.4 GBfile size, 2 parts | 61.9 GB59.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q4_K_SDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q4_K_S/CohereForAI_c4ai-command-a-03-2025-Q4_K_S-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q4_K_M | 62.5 GBfile size, 2 parts | 65.0 GB62.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q4_K_MDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q4_K_M/CohereForAI_c4ai-command-a-03-2025-Q4_K_M-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q4_K_L | 63.2 GBfile size, 2 parts | 65.7 GB63.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q4_K_LDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q4_K_L/CohereForAI_c4ai-command-a-03-2025-Q4_K_L-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q4_1 | 65.2 GBfile size, 2 parts | 67.7 GB65.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q4_1Download hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q4_1/CohereForAI_c4ai-command-a-03-2025-Q4_1-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q5_K_S | 71.5 GBfile size, 2 parts | 74.0 GB71.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q5_K_SDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q5_K_S/CohereForAI_c4ai-command-a-03-2025-Q5_K_S-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q5_K_M | 73.4 GBfile size, 2 parts | 75.9 GB73.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q5_K_MDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q5_K_M/CohereForAI_c4ai-command-a-03-2025-Q5_K_M-*-of-00002.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q6_K | 84.9 GBfile size, 3 parts | 87.4 GB84.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q6_KDownload hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q6_K/CohereForAI_c4ai-command-a-03-2025-Q6_K-*-of-00003.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
| Q8_0 | 109.9 GBfile size, 3 parts | 112.4 GB109.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q8_0Download hf download bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF --include "CohereForAI_c4ai-command-a-03-2025-Q8_0/CohereForAI_c4ai-command-a-03-2025-Q8_0-*-of-00003.gguf" --local-dir CohereForAI_c4ai-command-a-03-2025-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 3bitmlx-community/c4ai-command-a-03-2025-3bit | 45.3 GBfile size | 47.8 GB45.3 + 2.0 + 0.50 | Download page |
| MLX 4bitmlx-community/c4ai-command-a-03-2025-4bit | 58.2 GBfile size | 60.7 GB58.2 + 2.0 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 206.9 GBfile size | 209.4 GB206.9 + 2.0 + 0.50 |
hf download CohereLabs/c4ai-command-a-03-2025 --local-dir c4ai-command-a-03-2025Other conversions (10; sizes not read)
- unsloth/c4ai-command-a-03-2025-bnb-4bit bitsandbytes, 4bit, 459 downloads
- unsloth/c4ai-command-a-03-2025-unsloth-bnb-4bit bitsandbytes, 4bit, 69 downloads
- Tonic/c4ai-command-a-03-2025-4bit_fp4 bitsandbytes, 4bit, 36 downloads
- aikitoria/c4ai-command-a-03-2025-FP8-Dynamic FP8, 20 downloads
- Firworks/c4ai-command-a-03-2025-nvfp4 NVFP4, 20 downloads
- Tonic/c4ai-command-a-03-2025-4bit_nf4_no_double bitsandbytes, 4bit, 18 downloads
- gghfez/c4ai-command-a-03-2025-exl2-3bpw EXL2, 17 downloads
- Bedovyy/c4ai-command-a-03-2025-gptqmodel-4bit GPTQ, 4bit, 17 downloads
- gghfez/c4ai-command-a-03-2025-AWQ AWQ, 16 downloads
- lynnea1517/c4ai-command-a-03-2025-exl2-4.5bpw-test EXL2, 14 downloads
The Hub tags 29 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
1 provider serves this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| coherethe maker | ? | ? | ? | not given | 58 | 0.3 s | ? | yes | yes |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "CohereLabs/c4ai-command-a-03-2025:cohere", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- CohereLabs/command-a-vision-07-2025112B9.1kReviewed
- CohereLabs/command-a-reasoning-08-2025111B149Reviewed
- CohereLabs/command-a-translate-08-2025111B12Reviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:57 UTC. The repo. Found a mistake on this page? Tell us.