MiniMax-M1 80K on Apple M5 Ultra (512 GB)

Can the Apple M5 Ultra (512 GB) run MiniMax-M1 80K?

Yes, it runs well

Runs well. At Q4_K_M it needs about 310 GB of 384 GB usable, with an estimated speed of 25.3 tok/s.

Best quant: Q4_K_M
Generation speed: 25.3 tok/s
Prompt processing: 509 tok/s
First token (1K prompt): 2.0 s
Largest safe context: 976K

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

On macOS

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

Handy if you already work in Docker.

docker model run hf.co/MiniMaxAI/MiniMax-M1-80k

Text Generation WebUI

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 MiniMax-M1 80K

Original weights · Hugging Face

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

huggingface.co/MiniMaxAI/MiniMax-M1-80k (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (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 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.	35.5 / 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.	11.9 / 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	87.4 / 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`	214 GB	384 GB	39.7 tok/s	Runs great	58Good quality (B) · 58 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.	All files (opens in a new tab)
`Q3_K_M`	255 GB	384 GB	32.0 tok/s	Runs great	69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	310 GB	384 GB	25.3 tok/s	Runs well	78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	355 GB	384 GB	21.1 tok/s	Runs welltight fit	80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	406 GB	384 GB	15.2 tok/s	Runs wellover GPU memory limit	82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	515 GB	384 GB	—	Won't run	83Great quality (A) · 83 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.	All files (opens in a new tab)
`F16`	944 GB	384 GB	—	Won't run	83Great quality (A) · 83 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

78Great quality (A) · 78 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 · 17.7 tok/s · Runs well
58Good quality (B) · 58 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. Apple M3 Ultra (256 GB) Q2_K · 24.0 tok/s · Runs well (over GPU memory limit)
69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q3_K_M · 134 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X Q3_K_M · 113 tok/s · Runs well (tight fit)
69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q3_K_M · 137 tok/s · Runs well (tight fit)
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI300X Q2_K · 101 tok/s · Runs well (offloads to RAM)

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.