Check my GPU

LLMs ·

Command A (111B)

Parameters
111B
Architecture
Dense
Max context
256K tokens
License
cc-by-nc-4.0
Released
2025-03

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run command-a:111b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/c4ai-command-a-03-2025-GGUF (opens in a new tab)

ollama run hf.co/unsloth/c4ai-command-a-03-2025-GGUF

Original weights · Hugging Face

Full-precision files from Cohere, for fine-tuning, vLLM, Transformers.

huggingface.co/CohereLabs/c4ai-command-a-03-2025 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: sliding-window hybrid: 1 in 4 layers is global.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 44.4 GB 45.8 GB 48.0 GB GGUF (opens in a new tab)
Q3_K_M Low 54.4 GB 55.8 GB 58.0 GB GGUF · folder (opens in a new tab)
Q4_K_M Good 67.7 GB 69.1 GB 71.3 GB GGUF · folder (opens in a new tab)
Q5_K_M High 78.9 GB 80.2 GB 82.4 GB GGUF · folder (opens in a new tab)
Q6_K High 91.1 GB 92.4 GB 94.6 GB GGUF · folder (opens in a new tab)
Q8_0 Very high 118 GB 119 GB 121 GB GGUF · folder (opens in a new tab)
F16 Full 222 GB 223 GB 226 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Command A (111B)

The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at Q4_K_M.

Grade · points Hardware Quant Memory Speed Fit
84 ptsGreat (A) · 84 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell Q4_K_M 73.9 GB / 96.0 GB 19.8 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 35.6/45, Memory fit 25.0/25, Speed 5.5/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q6_K 104 GB / 144 GB 5.3 tok/s Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 5.4/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q4_K_M 76.8 GB / 96.0 GB 5.2 tok/s Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 35.6/45, Memory fit 25.0/25, Speed 5.5/15, Memory use 13.0/15 Apple M3 Ultra (256 GB) Q6_K 108 GB / 192 GB 5.4 tok/s Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 34.9/45, Memory fit 25.0/25, Speed 3.7/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q5_K_M 89.4 GB / 115 GB 2.5 tok/s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 3.7/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M 76.8 GB / 96.0 GB 2.4 tok/s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 35.6/45, Memory fit 25.0/25, Speed 5.5/15, Memory use 7.4/15 Apple M3 Ultra (512 GB) Q6_K 123 GB / 384 GB 5.4 tok/s Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 6.4/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q2_K 49.6 GB / 48.0 GB 7.3 tok/s Runs with offload
55 ptsUsable (C) · 55 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 5.5/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q2_K 49.6 GB / 48.0 GB 5.3 tok/s Runs with offload
48 ptsUsable (C) · 48 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 4.3/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q2_K 47.4 GB / 32.0 GB 3.3 tok/s Heavy offload

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.