c4ai-command-r7b-12-2024
CohereLabs CC BY-NC 4.0 out 22 months ago
8.03B parameters, text in, text out. 1 provider serves it.
Verified 2026-10-25 Rank #639 in LLMs · score 73.2 method v1 Sources 3 Downloads 30d 5.2k · #541 of 619 tracked
Where to run it
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | Cohere | — | — | — | — | Oct 25 |
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 28 quantized builds for local use.
- As a service1Cohere
- On own hardware28quantized builds
- Built on82 fine-tunes · 6 adapters · 0 merges
- In apps22Hugging Face Spaces
Top Spaces running it: reach-vb/2024-ai-timeline ♥ 467 · VIDraft/RAGOndevice ♥ 16 · aixsatoshi/NewModel-Test-Drive ♥ 5 · Steven10429/apply_lora_and_quantize ♥ 2
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 4.8 GB at INT4, 9.6 GB at FP8, 19 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
What people built on it
36 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
36 derivatives on the Hub, most of them quantized
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
Use-case evidence
4 use cases
What it is good at 4 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Facts
16 fields
Listed in LLMs
Facts
- c4ai-command-r7b-12-2024 has 8.03B parameters. (safetensors metadata, observed 2026-10-24)
- License: CC BY-NC 4.0 (friction: non-commercial). Non-commercial only; commercial hosting not permitted without a separate license. (license file, observed 2026-10-24)
- Created 2024-12-11, last modified 2025-10-30. (HF API, observed 2026-10-24)
- Access is gated on Hugging Face (auto). (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | Cohere2ForCausalLM |
| Model type | cohere2 |
| Params by dtype | BF16: 8,028,033,024 |
| Size band | M |
| MoE | no |
| Gated | auto |
| Papers | arXiv:2504.00698 |
| License | CC BY-NC 4.0 (cc-by-nc-4.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · Cohere2ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Cohere2ForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for c4ai-command-r7b-12-2024: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 19 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 9.6 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.8 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
All variants
36 variants
Lineage
quantized: 28finetune: 2adapter: 6
Top variants (36 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| bartowski/c4ai-command-r7b-12-2024-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | bartowski | 16 | 82.5k |
| Willy030125/command-r7b-12-2024-gguf | quantized | gguf | — | — | cc-by-nc-4.0 | Willy030125 | 0 | 42.9k |
| matrixportalx/c4ai-command-r7b-12-2024-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | matrixportalx | 1 | 11.6k |
| DevQuasar-6/CohereForAI.c4ai-command-r7b-12-2024-GGUF | quantized | GGUF | — | — | — | DevQuasar-6 | 7 | 10.7k |
| saidutta69/c4ai-command-r7b-12-2024-heretic | quantized | GGUF | 8.03B | M | other | saidutta69 | 3 | 5.4k |
| dranger003/c4ai-command-r7b-12-2024-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | dranger003 | 2 | 4.1k |
| oncu/c4ai-command-r7b-12-2024-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | oncu | 0 | 3.4k |
| Svngoku/c4ai-command-r7b-12-2024-4bit | quantized | -4bit | 8.25B | M | — | Svngoku | 1 | 1.8k |
| mlx-community/c4ai-command-r7b-12-2024-bf16 | finetune | -bf16 | 8.03B | M | cc-by-nc-4.0 | mlx-community | 4 | 1.3k |
| mlx-community/c4ai-command-r7b-12-2024-4bit | quantized | -4bit | 8.03B | M | cc-by-nc-4.0 | mlx-community | 0 | 1.2k |
| mlx-community/c4ai-command-r7b-12-2024-8bit | quantized | -8bit | 8.03B | M | cc-by-nc-4.0 | mlx-community | 0 | 790 |
| mobilint/c4ai-command-r7b-12-2024 | quantized | — | 1.05B | S | cc-by-nc-4.0 | mobilint | 0 | 715 |
| mlx-community/c4ai-command-r7b-12-2024-3bit | quantized | — | 8.03B | M | cc-by-nc-4.0 | mlx-community | 1 | 658 |
| Akatsuki-Amemiya/Nobihaza-trans-demo | quantized | GGUF | — | — | other | Akatsuki-Amemiya | 0 | 535 |
| mlx-community/c4ai-command-r7b-12-2024-6bit | quantized | — | 8.03B | M | cc-by-nc-4.0 | mlx-community | 0 | 533 |
| Lumia101/c4ai-command-r7b-12-2024-Q4_K_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | Lumia101 | 0 | 454 |
| msyukorai/c4ai-command-r7b-12-2024-Q4_0-GGUF | quantized | Q4_0 | — | — | cc-by-nc-4.0 | msyukorai | 0 | 336 |
| Lumia101/c4ai-command-r7b-12-2024-bnb-4bit | quantized | -bnb | 8.03B | M | cc-by-nc-4.0 | Lumia101 | 0 | 303 |
| Lucy-in-the-Sky/c4ai-command-r7b-12-2024-Q8_0-GGUF | quantized | Q8_0 | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 300 |
| ncux/c4ai-command-r7b-12-2024-Q4_0-GGUF | quantized | Q4_0 | — | — | cc-by-nc-4.0 | ncux | 0 | 296 |
| huggingkot/c4ai-command-r7b-12-2024-Q4_K_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | huggingkot | 0 | 295 |
| turboderp/c4ai-command-r7b-12-2024-exl3 | quantized | exl3 | — | — | cc-by-nc-4.0 | turboderp | 1 | 234 |
| Lucy-in-the-Sky/c4ai-command-r7b-12-2024-IQ3_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 283 |
| Lucy-in-the-Sky/c4ai-command-r7b-12-2024-Q6_K-GGUF | quantized | Q6_K | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 276 |
| milk639/Miel | quantized | — | 8.03B | M | cc-by-nc-4.0 | milk639 | 0 | 254 |
| Anthonyg5005/c4ai-command-r7b-12-2024-exl2 | quantized | exl2 | — | — | cc-by-nc-4.0 | Anthonyg5005 | 0 | 218 |
| milk639/Tara | quantized | — | 8.25B | M | — | milk639 | 0 | 216 |
| Lucy-in-the-Sky/c4ai-command-r7b-12-2024-Q2_K-GGUF | quantized | Q2_K | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 180 |
| Lucy-in-the-Sky/c4ai-command-r7b-12-2024-Q4_K_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 172 |
| Niazi/c4ai-command-r7b-12-2024-languages | adapter | — | — | — | — | Niazi | 0 | 63 |
| nqzfaizal77ai/vectoris-impero-reinit-550m-zero | finetune | — | 559M | S | — | nqzfaizal77ai | 0 | 60 |
| Niazi/c4ai-command-r7b-12-2024-Qlora_bengali | adapter | — | — | — | — | Niazi | 0 | 47 |
| Niazi/Cohere-c4ai-command-r7b-12-2024-Sawahili | adapter | — | — | — | — | Niazi | 0 | 46 |
| Niazi/c4ai-command-r7b-12-2024-Thai | adapter | — | — | — | — | Niazi | 0 | 40 |
| Agenix-AI/ARZ-LLM-CHECKPOINTS | adapter | — | — | — | — | Agenix-AI | 0 | 29 |
| rshahbaz/news-summarizer-command-r7b | adapter | — | — | — | cc-by-nc-4.0 | rshahbaz | 0 | 14 |
All providers
1 provider · 1 endpoint
Where to run 1 providers · 1 endpoints
Hosted endpoints observed for c4ai-command-r7b-12-2024, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Cohere hf | command-r7b-12-2024 | — | — | — | — | 78.3 | 229 ms | yes | live | 2026-10-25 |
Papers
1 paper
Papers 1
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Similar models
3 models
Similar models
- Llama-3.1-8B-Instruct · 8.03B same size band (M), same task (text-generation), more providers
- Qwen3-8B · 8.19B same size band (M), same task (text-generation), more providers, permissive license
- Meta-Llama-3-8B-Instruct · 8.03B same size band (M), same task (text-generation), more providers
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:42 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:13 UTC · Last verified 2026-10-25
Follow c4ai-command-r7b-12-2024
Watch this model
- /feeds/models/CohereLabs--c4ai-command-r7b-12-2024.xml(RSS 2.0) · every change to c4ai-command-r7b-12-2024
- /feeds/families/CohereLabs--c4ai-command.xml(RSS 2.0) · every change across the c4ai-command family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.