Command R+ 104B (04-2024) on NVIDIA RTX PRO 6000 Blackwell

Can the NVIDIA RTX PRO 6000 Blackwell run Command R+ 104B (04-2024)?

Yes, it runs well

Runs well. At Q4_K_M it needs about 70.9 GB of 96.0 GB usable, with an estimated speed of 21.2 tok/s.

Best quant: Q4_K_M
Generation speed: 21.2 tok/s
Prompt processing: 867 tok/s
First token (1K prompt): 1.2 s
Largest safe context: 101K

Best app to run it on the NVIDIA RTX PRO 6000 Blackwell

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Command R+ 104B (04-2024) in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Command R+ 104B (04-2024) in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? Command R+ 104B (04-2024) 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+ 104B (04-2024)

Recommended for the NVIDIA RTX PRO 6000 Blackwell: Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q4_K_M files (opens in a new tab)

huggingface.co/bartowski/c4ai-command-r-plus-GGUF (opens in a new tab)

ollama run hf.co/bartowski/c4ai-command-r-plus-GGUF

Original weights · Hugging Face

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

huggingface.co/CohereLabs/c4ai-command-r-plus (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 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, 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 well: How well it runs on the NVIDIA RTX PRO 6000 Blackwell: 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.	27.4 / 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.	10.9 / 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	78.3 / 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 RTX PRO 6000 Blackwell

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	49.1 GB	96.0 GB	34.8 tok/s	Runs great	44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	58.4 GB	96.0 GB	27.4 tok/s	Runs well	53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	70.9 GB	96.0 GB	21.2 tok/s	Runs well	60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	81.3 GB	96.0 GB	17.5 tok/s	Runs well	62Good quality (B) · 62 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	92.7 GB	96.0 GB	14.7 tok/s	Runs welltight fit	63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	118 GB	96.0 GB	—	Won't run	64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	215 GB	96.0 GB	—	Won't run	64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (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

53Fair quality (C) · 53 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 M2 Ultra (192 GB) Q3_K_M · 10.5 tok/s · Runs well
53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q3_K_M · 10.8 tok/s · Runs well
53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q3_K_M · 10.8 tok/s · Runs well
64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 Q8_0 · 48.2 tok/s · Runs great
63Good quality (B) · 63 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. NVIDIA H200 141GB SXM Q6_K · 39.4 tok/s · Runs great
63Good quality (B) · 63 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. NVIDIA H200 NVL Q6_K · 39.4 tok/s · Runs great

Quick answers

How much memory does Command R+ 104B (04-2024) need on the NVIDIA RTX PRO 6000 Blackwell 96GB?

At Q4_K_M it needs about 70.9 GB. The NVIDIA RTX PRO 6000 Blackwell 96GB has 96.0 GB usable.

How fast is Command R+ 104B (04-2024) on the NVIDIA RTX PRO 6000 Blackwell 96GB?

About 21.2 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Command R+ 104B (04-2024) should I use on the NVIDIA RTX PRO 6000 Blackwell 96GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.