on

Can the Apple M3 Ultra (512 GB) run North Micro Vision?

44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At F16 it needs about 37.2 GB of 384 GB usable, with an estimated speed of 81.9 tok/s.

Best quant
F16
Generation speed
81.9 tok/s
Prompt processing
7,100 tok/s
First token (1K prompt)
0.3 s
Largest safe context
488K

Best app to run it on the Apple M3 Ultra (512 GB)

On macOS

LM Studio

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

  • Runs the MLX build, typically 35–90% faster than GGUF for a model with 2.5B active parameters on Apple silicon.
  • Point-and-click: search, download and chat in one window.

Open North Micro Vision in LM Studio

  • MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 2.5B active parameters on Apple silicon.
  • Unsloth Desktop Runs the MLX build, typically 35–90% faster than GGUF for a model with 2.5B active parameters on Apple silicon.

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 North Micro Vision

Original weights · Hugging Face

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

huggingface.co/CohereLabs/North-Micro-Vision-Instruct (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 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at F16, 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 M3 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.19.8 / 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.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.2.2 / 15
Match score62.0 / 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 M3 Ultra (512 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 33.3 GB 384 GB 573 tok/s Runs great 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 33.5 GB 384 GB 451 tok/s Runs great 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 33.8 GB 384 GB 349 tok/s Runs great 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 34.0 GB 384 GB 288 tok/s Runs great 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 34.3 GB 384 GB 242 tok/s Runs great 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 34.9 GB 384 GB 178 tok/s Runs great 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 37.2 GB 384 GB 81.9 tok/s Runs great 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (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

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.

Was this page helpful?