← Ministral 3
Ministral 3 logo

Ministral 3 8B-INSTRUCT-2512

No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.

Be the first to measure it It needs about 2.5 GB; 17 of 18 kinds of machine on the network can hold it. The first machine to sign a result takes 10 points on the providers board.What is measured in Ministral 3 The members of this family that machines have already run, with their speed, price and context.

What it fits on

The smallest build needs about 2.5 GB; 17 of 18 kinds of machine on the network can hold it. Bars: each kind's memory (its card's, else RAM) · ticks: every build, at the size it held plus a fifth for the prompt.

  1. Linux, CPU only · 2 CPUs1 GB RAMnone
  2. NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the card3 of 9
  3. NVIDIA GeForce GTX 16504 GB on the card3 of 9
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAM5 of 9
  5. Windows, CPU only · 12 CPUs7 GB RAM5 of 9
  6. Apple silicon8 GB RAM5 of 9
  7. Apple M18 GB RAM5 of 9
  8. Mac, CPU only · 8 CPUs8 GB RAM5 of 9
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the card6 of 9
  10. Tesla T415 GB on the card6 of 9
  11. Intel(R) UHD Graphics 73016 GB RAM6 of 9
  12. Intel(R) Iris(R) Xe Graphics16 GB RAM6 of 9
  13. Apple M416 GB RAM6 of 9
  14. Apple M116 GB RAM6 of 9
  15. NVIDIA L422 GB on the card8 of 9
  16. 2× Tesla T429 GB on the card8 of 9
  17. Linux, CPU only · 4 CPUs31 GB RAM8 of 9
  18. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery build
hf.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF:IQ1_Sollama · IQ1_S · 2.1 GiB · quantizer (unsloth)
hf.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF:IQ2_XXSollama · IQ2_XXS · 2.5 GiB · quantizer (unsloth)
hf.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF:IQ3_XXSollama · IQ3_XXS · 3.3 GiB · quantizer (unsloth)
hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_Mollama · Q4_K_M · 4.8 GiB · vendor (mistralai)
hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q5_K_Mollama · Q5_K_M · 5.6 GiB · vendor (mistralai)
hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q8_0ollama · Q8_0 · 8.4 GiB · vendor (mistralai)
mlx-community/Ministral-3-8B-Instruct-2512mlx · FP8 · 15.8 GiB · quantizer (mlx-community)
hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:BF16ollama · BF16 · 15.8 GiB · vendor (mistralai)
mistralai/Ministral-3-8B-Instruct-2512-BF16vllm · BF16 · 33.2 GiB · vendor (mistralai)