c4ai-command-r-v01
CohereLabs CC BY-NC 4.0 out 3 years ago
35.0B parameters, text in, text out.
Verified 2026-10-25 Rank #728 in LLMs · score 71.7 method v1 Sources 3 Downloads 30d 3.8k · #559 of 619 tracked
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.
No API provider serves it, so its downloads are people running it themselves: 16 quantized builds and 100 Spaces.
- As a service0no API provider listed
- On own hardware16quantized builds
- Built on97 fine-tunes · 2 adapters · 0 merges
- In apps100+Hugging Face Spaces
Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · Tonic/Command-R ♥ 15 · AFischer1985/AI-RAG-Interface-to-Hub ♥ 8 · awacke1/Deepseek-HPC-GPU-KEDA ♥ 5
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 64 GB Mac (unified memory) at INT4
About 21 GB at INT4, 42 GB at FP8, 84 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
25 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
25 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
2 use cases
What it is good at 2 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
15 fields
Listed in LLMs
Facts
- c4ai-command-r-v01 has 35.0B 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 2024-03-11, last modified 2025-04-16. (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 | CohereForCausalLM |
| Model type | cohere |
| Params by dtype | F16: 34,980,831,232 |
| Size band | L |
| MoE | no |
| Gated | auto |
| License | CC BY-NC 4.0 (cc-by-nc-4.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · CohereForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · CohereForCausalLM · 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-r-v01: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 84 GB · Multi-GPU node (<640 GB) |
|---|---|
| FP8 (1 byte/param) | 42 GB · Single high-end GPU (<80 GB) |
| INT4 (0.5 bytes/param) | 21 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
All variants
25 variants
Lineage
quantized: 16finetune: 7adapter: 2
Top variants (25 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| DavidAU/Command-R-01-Ultra-NEO-V1-35B-IMATRIX-GGUF | quantized | IMATRIX | — | — | apache-2.0 | DavidAU | 27 | 118.2k |
| DavidAU/Command-R-01-Ultra-NEO-DARK-HORROR-V1-V2-35B-IMATRIX-GGUF | quantized | IMATRIX | — | — | apache-2.0 | DavidAU | 31 | 111.9k |
| qwp4w3hyb/c4ai-command-r-v01-iMat-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | qwp4w3hyb | 13 | 56.3k |
| dranger003/c4ai-command-r-v01-iMat.GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | dranger003 | 27 | 38.4k |
| second-state/C4AI-Command-R-v01-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | second-state | 1 | 21.3k |
| mradermacher/c4ai-command-r-v01-i1-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | mradermacher | 3 | 17.9k |
| mradermacher/c4ai-command-r-v01-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | mradermacher | 1 | 13.4k |
| backyardai/c4ai-command-r-v01-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | backyardai | 0 | 12.7k |
| Aratako/c4ai-command-r-v01-japanese-instruct | finetune | — | 35.0B | L | cc-by-nc-sa-4.0 | Aratako | 4 | 8.4k |
| DevQuasar/CohereLabs.c4ai-command-r-v01-GGUF | quantized | GGUF | — | — | — | DevQuasar | 1 | 3.2k |
| newsletter/c4ai-command-r-v01-Q4_K_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | newsletter | 1 | 2.9k |
| tensorblock/c4ai-command-r-v01-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | tensorblock | 1 | 2.9k |
| jukofyork/command-r-35b-writer-v2 | finetune | — | 35.0B | L | cc-by-nc-4.0 | jukofyork | 0 | 678 |
| jukofyork/command-r-35b-writer-v3 | finetune | — | 35.0B | L | cc-by-nc-4.0 | jukofyork | 3 | 363 |
| ggnoy/c4ai-command-r-v01-Q5_K_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | ggnoy | 0 | 373 |
| Lucy-in-the-Sky/c4ai-command-r-v01-Q4_K_M-GGUF | quantized | GGUF | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 343 |
| jukofyork/command-r-35b-writer | finetune | — | 35.0B | L | cc-by-nc-4.0 | jukofyork | 1 | 253 |
| Citaman/command-r-39-layer | finetune | — | 36.3B | XL | — | Citaman | 0 | 228 |
| Lucy-in-the-Sky/c4ai-command-r-v01-Q8_0-GGUF | quantized | Q8_0 | — | — | cc-by-nc-4.0 | Lucy-in-the-Sky | 0 | 154 |
| Downtown-Case/jukofyork_command-r-35b-writer-v3-exl3-3.75bpw-hb6 | quantized | exl3 | 10.6B | L | cc-by-nc-4.0 | Downtown-Case | 1 | 99 |
| ubitech-edg/commandr-35b-cpt | adapter | — | 35.0B | L | apache-2.0 | ubitech-edg | 0 | 70 |
| ubitech-edg/commandr-35b-sft | adapter | — | 35.0B | L | apache-2.0 | ubitech-edg | 0 | 53 |
| TNT3530/Command-R-q4f16_1-MLC | quantized | — | — | — | — | TNT3530 | 0 | 0 |
| gghfexp/c4ai-command-r-jlens | finetune | — | — | — | cc-by-nc-4.0 | gghfexp | 0 | 0 |
| gghfez/c4ai-command-r-v01-jacobian-lens | finetune | — | — | — | cc-by-nc-4.0 | gghfez | 0 | 0 |
Similar models
3 models
Similar models
- Qwen3-32B · 32.8B same size band (L), same task (text-generation), more providers, permissive license
- Qwen2.5-Coder-32B-Instruct · 32.8B same size band (L), same task (text-generation), more providers, permissive license
- DeepSeek-R1-Distill-Qwen-32B · 32.8B same size band (L), same task (text-generation), more providers, permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:11 UTC · Last verified 2026-10-25
Follow c4ai-command-r-v01
Watch this model
- /feeds/models/CohereLabs--c4ai-command-r-v01.xml(RSS 2.0) · every change to c4ai-command-r-v01
- /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.