- Size
- 32.3B 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
- 19 Aug 2024the date the repo was created
- Context length
- Not known
- Kind
- Base model (no base model declared on the Hub)CohereForCausalLM
- On Hugging Face
- CohereLabs/c4ai-command-r-08-2024189 downloads in the last 30 days, 175 likes
Scores
- default setting46.4%conceptualreasoning.ai
Epoch's name: c4ai-command-r-08-2024. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- default setting27.5%LiveBench Leaderboard
Epoch's name: c4ai-command-r-08-2024. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 results
- default setting9.2%4.1 to 14.3conceptualreasoning.ai
Epoch's name: c4ai-command-r-08-2024. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- Shots: 565.2%Stanford CRFM Leaderboard
Epoch's name: c4ai-command-r-08-2024. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 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, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
bartowski/c4ai-command-r-08-2024-GGUF (converted by bartowski), 2.9k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XS | 13.1 GBfile size | 15.6 GB13.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:IQ3_XSDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-IQ3_XS.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q3_K_S | 13.7 GBfile size | 16.2 GB13.7 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_SDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q3_K_S.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| IQ3_M | 14.2 GBfile size | 16.7 GB14.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:IQ3_MOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:IQ3_MDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-IQ3_M.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q3_K_M | 15.1 GBfile size | 17.6 GB15.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_MOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_MDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q3_K_M.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q3_K_L | 16.4 GBfile size | 18.9 GB16.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_LOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_LDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q3_K_L.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| IQ4_XS | 16.6 GBfile size | 19.1 GB16.6 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:IQ4_XSOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:IQ4_XSDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-IQ4_XS.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q3_K_XL | 16.8 GBfile size | 19.3 GB16.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_XLOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q3_K_XLDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q3_K_XL.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_0_4_4 | 17.4 GBfile size | 19.9 GB17.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_0_4_4Ollama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_0_4_4Download hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_0_4_4.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_0_4_8 | 17.4 GBfile size | 19.9 GB17.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_0_4_8Ollama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_0_4_8Download hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_0_4_8.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_0_8_8 | 17.4 GBfile size | 19.9 GB17.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_0_8_8Ollama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_0_8_8Download hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_0_8_8.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_0 | 17.5 GBfile size | 20.0 GB17.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_0Ollama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_0Download hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_0.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_K_S | 17.6 GBfile size | 20.1 GB17.6 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_K_SOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_K_SDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_K_S.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_K_M | 18.4 GBfile size | 20.9 GB18.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_K_MDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_K_M.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q4_K_L | 18.9 GBfile size | 21.4 GB18.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q4_K_LOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q4_K_LDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q4_K_L.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q5_K_S | 20.9 GBfile size | 23.4 GB20.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q5_K_SOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q5_K_SDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q5_K_S.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q5_K_M | 21.5 GBfile size | 24.0 GB21.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q5_K_MOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q5_K_MDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q5_K_M.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q5_K_L | 21.9 GBfile size | 24.4 GB21.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q5_K_LOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q5_K_LDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q5_K_L.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q6_K | 24.7 GBfile size | 27.2 GB24.7 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q6_KOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q6_KDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q6_K.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q6_K_L | 25.2 GBfile size | 27.7 GB25.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q6_K_LOllama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q6_K_LDownload hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q6_K_L.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| Q8_0 | 32.0 GBfile size | 34.5 GB32.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:Q8_0Ollama ollama run hf.co/bartowski/c4ai-command-r-08-2024-GGUF:Q8_0Download hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-Q8_0.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
| F16 | 60.2 GBfile size, 2 parts | 62.7 GB60.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/c4ai-command-r-08-2024-GGUF:F16Download hf download bartowski/c4ai-command-r-08-2024-GGUF --include "c4ai-command-r-08-2024-f16/c4ai-command-r-08-2024-f16-*-of-00002.gguf" --local-dir c4ai-command-r-08-2024-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F16original weights | 60.2 GBfile size | 62.7 GB60.2 + 2.0 + 0.50 |
hf download CohereLabs/c4ai-command-r-08-2024 --local-dir c4ai-command-r-08-2024Other conversions (8; sizes not read)
- unsloth/c4ai-command-r-08-2024-bnb-4bit bitsandbytes, 4bit, 180 downloads
- turboderp/c4ai-command-r-08-2024-exl3 EXL3, 18 downloads
- bullerwins/c4ai-command-r-08-2024-exl2_4.0bpw EXL2, 15 downloads
- bullerwins/c4ai-command-r-08-2024-exl2_6.0bpw EXL2, 12 downloads
- bullerwins/c4ai-command-r-08-2024-exl2_8.0bpw EXL2, 12 downloads
- bullerwins/c4ai-command-r-08-2024-exl2_3.0bpw EXL2, 12 downloads
- MetaphoricalCode/c4ai-command-r-08-2024-exl3-4.65bpw-hb6 EXL3, 11 downloads
- models123/c4ai-command-r-08-2024-bnb-4bit bitsandbytes, 4bit, 8 downloads
The Hub tags 28 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 | 7 | 0.4 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-r-08-2024: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.
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.