Check my GPU

LLMs ·

Command R+ (08-2024) 104B

Parameters
104B
Architecture
Dense
Max context
128K tokens
License
cc-by-nc-4.0
Released
2024-08

How to run it

Quickest · Ollama

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

ollama run command-r-plus:104b

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/lmstudio-community/c4ai-command-r-plus-08-2024-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/c4ai-command-r-plus-08-2024-GGUF

Original weights · Hugging Face

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

huggingface.co/CohereLabs/c4ai-command-r-plus-08-2024 (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.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 41.5 GB 44.3 GB 50.7 GB
Q3_K_M Low 50.9 GB 53.6 GB 60.1 GB GGUF (Q3_K_L) · part 1 of 2 (opens in a new tab)
Q4_K_M Good 63.3 GB 66.1 GB 72.5 GB GGUF · part 1 of 2 (opens in a new tab)
Q5_K_M High 73.7 GB 76.5 GB 82.9 GB
Q6_K High 85.1 GB 87.9 GB 94.3 GB GGUF · part 1 of 3 (opens in a new tab)
Q8_0 Very high 110 GB 113 GB 119 GB
F16 Full 208 GB 210 GB 217 GB Original weights (opens in a new tab)

Best hardware for Command R+ (08-2024) 104B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon PRO W7800 48GB (launch price $2,799) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
80 ptsGreat (A) · 80 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell Q4_K_M 70.9 GB / 96.0 GB 21.2 tok/s Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q6_K 99.4 GB / 144 GB 5.7 tok/s Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q4_K_M 73.8 GB / 96.0 GB 5.6 tok/s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q6_K 97.1 GB / 115 GB 2.2 tok/s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 5.7/15, Memory use 12.4/15 Apple M3 Ultra (256 GB) Q6_K 103 GB / 192 GB 5.8 tok/s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 3.8/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M 73.8 GB / 96.0 GB 2.6 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 5.7/15, Memory use 7.1/15 Apple M3 Ultra (512 GB) Q6_K 119 GB / 384 GB 5.8 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 22.1/45, Memory fit 10.0/25, Speed 6.6/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q2_K 48.1 GB / 48.0 GB 7.8 tok/s Runs with offload
52 ptsUsable (C) · 52 of 100 points: Model quality 22.1/45, Memory fit 10.0/25, Speed 5.7/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q2_K 48.1 GB / 48.0 GB 5.7 tok/s Runs with offload
45 ptsUsable (C) · 45 of 100 points: Model quality 22.1/45, Memory fit 4.0/25, Speed 4.5/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q2_K 45.9 GB / 32.0 GB 3.6 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.