Check my GPU

LLMs ·

North Micro Vision

Parameters
2.5B
Architecture
Dense
Max context
488K tokens
License
apache-2.0
Released
2026-08

How to run it

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 6 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 1.0 GB 2.5 GB 5.4 GB All files (opens in a new tab)
Q3_K_M Low 1.2 GB 2.8 GB 5.6 GB All files (opens in a new tab)
Q4_K_M Good 1.5 GB 3.1 GB 5.9 GB All files (opens in a new tab)
Q5_K_M High 1.8 GB 3.3 GB 6.1 GB All files (opens in a new tab)
Q6_K High 2.0 GB 3.6 GB 6.4 GB All files (opens in a new tab)
Q8_0 Very high 2.6 GB 4.2 GB 7.0 GB All files (opens in a new tab)
F16 Full 5.0 GB 6.5 GB 9.3 GB Original weights (opens in a new tab)

Best hardware for North Micro Vision

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q6_K.

Grade · points Hardware Quant Memory Speed Fit
73 ptsGreat (A) · 73 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 Intel Arc B580 F16 7.1 GB / 12.0 GB 40.5 tok/s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 NVIDIA GeForce RTX 3060 12GB F16 7.1 GB / 12.0 GB 41.8 tok/s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 NVIDIA GeForce RTX 4070 SUPER F16 7.1 GB / 12.0 GB 58.5 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15 NVIDIA GeForce RTX 4060 Q8_0 4.6 GB / 8.0 GB 68.5 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 AMD Radeon RX 9070 XT F16 7.3 GB / 16.0 GB 64.0 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 7.3 GB / 16.0 GB 78.0 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 NVIDIA GeForce RTX 4080 SUPER F16 7.3 GB / 16.0 GB 85.5 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 NVIDIA GeForce RTX 5060 Ti 16GB F16 7.3 GB / 16.0 GB 52.0 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 NVIDIA GeForce RTX 5070 Ti F16 7.3 GB / 16.0 GB 104 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 NVIDIA GeForce RTX 5080 F16 7.3 GB / 16.0 GB 111 tok/s Runs well

Check it on your own hardware

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.