Command R+ (08-2024) 104B on NVIDIA B200

Can the NVIDIA B200 run Command R+ (08-2024) 104B?

Yes, it runs great

Runs great. At Q8_0 it needs about 122 GB of 180 GB usable, with an estimated speed of 48.2 tok/s.

Best quant: Q8_0
Generation speed: 48.2 tok/s
Prompt processing: 1,110 tok/s
First token (1K prompt): 0.9 s
Largest safe context: 128K

Best app to run it on the NVIDIA B200

On Linux

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve CohereLabs/c4ai-command-r-plus-08-2024

Ollama One command with Ollama’s own build of this model.
LM Studio Point-and-click: search, download and chat in one window.

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run command-r-plus:104b-08-2024-q8_0

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

Want an agent? Command R+ (08-2024) 104B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Command R+ (08-2024) 104B

Recommended for the NVIDIA B200: Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

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

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

ollama run command-r-plus:104b-08-2024-q8_0

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 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA B200: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	31.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	86.5 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA B200

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	53.3 GB	180 GB	155 tok/s	Runs great	49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	62.6 GB	180 GB	122 tok/s	Runs great	58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q3_K_L) · part 1 of 2 (opens in a new tab)
`Q4_K_M`	75.1 GB	180 GB	94.6 tok/s	Runs great	66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 2 (opens in a new tab)
`Q5_K_M`	85.5 GB	180 GB	78.1 tok/s	Runs great	67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	96.9 GB	180 GB	65.6 tok/s	Runs great	69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 3 (opens in a new tab)
`Q8_0`	122 GB	180 GB	48.2 tok/s	Runs great	70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.
`F16`	219 GB	180 GB	—	Won't run	70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q4_K_M · 21.2 tok/s · Runs well
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q3_K_M · 10.5 tok/s · Runs well
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q3_K_M · 10.8 tok/s · Runs well
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q3_K_M · 10.8 tok/s · Runs well
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXM Q6_K · 39.4 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 NVL Q6_K · 39.4 tok/s · Runs great

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.