Command R (08-2024) 32B on Apple M5 Ultra (512 GB)

Can the Apple M5 Ultra (512 GB) run Command R (08-2024) 32B?

Yes, it runs great

Runs great. At Q4_K_M it needs about 52.4 GB of 384 GB usable, with an estimated speed of 39.3 tok/s.

Best quant: Q4_K_M
Generation speed: 39.3 tok/s
Prompt processing: 724 tok/s
First token (1K prompt): 1.4 s
Largest safe context: 128K

Best app to run it on the Apple M5 Ultra (512 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Runs the MLX build, typically up to 10% faster than GGUF for a model with 32.3B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Command R (08-2024) 32B in LM Studio

Ollama One command with Ollama’s own build of this model.
llama.cpp Usually the first to support new model architectures.

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) 32B

Recommended for the Apple M5 Ultra (512 GB): Q4_K_M. 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:35b-08-2024-q4_K_M

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

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

ollama run hf.co/lmstudio-community/c4ai-command-r-08-2024-GGUF:Q4_K_M

Original weights · Hugging Face

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

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

How it’s rated

Quality 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (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 great: How well it runs on the Apple M5 Ultra (512 GB): 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.	26.5 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	14.9 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.1 / 15
Match score	69.5 / 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 Apple M5 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	45.6 GB	384 GB	64.5 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	48.5 GB	384 GB	50.8 tok/s	Runs great	52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q3_K_L) (opens in a new tab)
`Q4_K_M`	52.4 GB	384 GB	39.3 tok/s	Runs great	58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	55.6 GB	384 GB	32.4 tok/s	Runs great	60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	59.1 GB	384 GB	27.2 tok/s	Runs well	61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	66.9 GB	384 GB	20.0 tok/s	Runs well	62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	97.3 GB	384 GB	9.2 tok/s	Slow	62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (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

60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q5_K_M · 56.3 tok/s · Runs great
58Good quality (B) · 58 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 GeForce RTX 4090 Q4_K_M · 38.3 tok/s · Runs well (tight fit)
58Good quality (B) · 58 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. NVIDIA GeForce RTX 3090 Q4_K_M · 35.6 tok/s · Runs well (tight fit)
58Good quality (B) · 58 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. AMD Radeon RX 7900 XTX Q4_K_M · 31.4 tok/s · Runs well (tight fit)
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 47.3 tok/s · Runs great
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 17.9 tok/s · Runs well

Quick answers

How much memory does Command R (08-2024) 32B need on the M5 Ultra 512GB?

At Q4_K_M it needs about 52.4 GB. The M5 Ultra 512GB has 384 GB usable.

How fast is Command R (08-2024) 32B on the M5 Ultra 512GB?

About 39.3 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 (08-2024) 32B should I use on the M5 Ultra 512GB?

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.