← Step 3.7
Step 3.7 logo

Step-3.7-Flash-Q4_K_M-MTP-GGUF

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.

What it fits on

The smallest build needs about 3.2 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 card1 of 4
  3. NVIDIA GeForce GTX 16504 GB on the card1 of 4
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAM2 of 4
  5. Windows, CPU only · 12 CPUs7 GB RAM2 of 4
  6. Apple silicon8 GB RAM3 of 4
  7. Apple M18 GB RAM3 of 4
  8. Mac, CPU only · 8 CPUs8 GB RAM3 of 4
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the card3 of 4
  10. Tesla T415 GB on the card3 of 4
  11. Intel(R) UHD Graphics 73016 GB RAM3 of 4
  12. Intel(R) Iris(R) Xe Graphics16 GB RAM3 of 4
  13. Apple M416 GB RAM3 of 4
  14. Apple M116 GB RAM3 of 4
  15. NVIDIA L422 GB on the card3 of 4
  16. 2× Tesla T429 GB on the card3 of 4
  17. Linux, CPU only · 4 CPUs31 GB RAM3 of 4
  18. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the card3 of 4
hf.co/notSnix/Step-3.7-Flash-Q4_K_M-MTP-GGUF:Q6_Kollama · Q6_K · 2.7 GiB · derivative (notSnix)
hf.co/notSnix/Step-3.7-Flash-Q4_K_M-MTP-GGUF:Q8_0ollama · Q8_0 · 3.5 GiB · derivative (notSnix)
hf.co/notSnix/Step-3.7-Flash-Q4_K_M-MTP-GGUF:BF16ollama · BF16 · 6.5 GiB · derivative (notSnix)
hf.co/notSnix/Step-3.7-Flash-Q4_K_M-MTP-GGUF:Q4_K_Mollama · Q4_K_M · 110.4 GiB · derivative (notSnix)