Command A+ (218B-A25B) on AMD Ryzen AI Max+ 395 (128 GB)

Can the AMD Ryzen AI Max+ 395 (128 GB) run Command A+ (218B-A25B)?

Yes, it runs well (over GPU memory limit)

Runs well (over GPU memory limit). At Q2_K it needs about 96.0 GB of 96.0 GB usable, with an estimated speed of 14.3 tok/s.

Best quant: Q2_K
Generation speed: 14.3 tok/s
Prompt processing: 1,473 tok/s
First token (1K prompt): 0.7 s
Largest safe context: 6K

Best app to run it on the AMD Ryzen AI Max+ 395 (128 GB)

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

Splits the model between GPU memory and system RAM, which this setup needs.
Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull bartowski/command-a-plus-05-2026-GGUF:Q2_K

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
LM Studio Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

Splits the model between GPU memory and system RAM, which this setup needs.
Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull bartowski/command-a-plus-05-2026-GGUF:Q2_K

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
LM Studio Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? Command A+ (218B-A25B) 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 A+ (218B-A25B)

Recommended for the AMD Ryzen AI Max+ 395 (128 GB): Q2_K. 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 Q2_K files (opens in a new tab)

huggingface.co/bartowski/command-a-plus-05-2026-GGUF (opens in a new tab)

ollama run hf.co/bartowski/command-a-plus-05-2026-GGUF

Original weights · Hugging Face

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

huggingface.co/CohereLabs/command-a-plus-05-2026-bf16 (opens in a new tab)

No sign-in needed.

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 wellover GPU memory limit: How well it runs on the AMD Ryzen AI Max+ 395 (128 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.	27.7 / 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.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.0 / 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	61.7 / 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 AMD Ryzen AI Max+ 395 (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	96.0 GB	96.0 GB	14.3 tok/s	Runs wellover GPU memory limit	61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q3_K_M`	116 GB	96.0 GB	11.4 tok/s	Slowfar over GPU memory limit	73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	142 GB	96.0 GB	—	Won't run	83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	164 GB	96.0 GB	—	Won't run	85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	188 GB	96.0 GB	—	Won't run	87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	240 GB	96.0 GB	—	Won't run	88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	446 GB	96.0 GB	—	Won't run	88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (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

83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q4_K_M · 31.0 tok/s · Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q3_K_M · 38.3 tok/s · Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 31.0 tok/s · Runs great
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q2_K · 99.6 tok/s · Runs well (tight fit)
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q2_K · 20.6 tok/s · Runs well
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q2_K · 22.5 tok/s · Runs well (tight fit)

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.