family member
Qwen 3.5 logo

Qwen 3.5 9B

2.4 tokens a second on a machine not reported. OpenRouter sells it at $0.11 per million output tokens.

2 builds of Qwen 3.5 9B, 3 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.

2.5tok/s, fastest machine
6.3 GBmemory, smallest build
3providers measured it
Run it on your gram Install a gram with one command. It works through the catalog on your own machine and signs every result. 3 providers have measured Qwen 3.5 9B so far.Use it in your own room Ask Evo in your gramx and it runs on a machine that proved it. On your own machines it costs you nothing.Compare every build Put it beside every other model in one table: speed, price, context and the API price, one row each.
best on ollama · 2 builds

no context proved on this engine yet

2.5 tok/s peak, by unsloth Q8_0

What it fits on

The smallest build needs about 6.3 GB; 15 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 cardnone
  3. NVIDIA GeForce GTX 16504 GB on the cardnone
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAM1 of 2
  5. Windows, CPU only · 12 CPUs7 GB RAM1 of 2
  6. Apple silicon8 GB RAM1 of 2
  7. Apple M18 GB RAM1 of 2
  8. Mac, CPU only · 8 CPUs8 GB RAM1 of 2
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the cardevery build
  10. Tesla T415 GB on the cardevery build
  11. Intel(R) UHD Graphics 73016 GB RAMevery build
  12. Intel(R) Iris(R) Xe Graphics16 GB RAMevery build
  13. Apple M416 GB RAMevery build
  14. Apple M116 GB RAMevery build
  15. NVIDIA L422 GB on the cardevery build
  16. 2× Tesla T429 GB on the cardevery build
  17. Linux, CPU only · 4 CPUs31 GB RAMevery build
  18. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery build

Measured by

The people whose machines signed these numbers

Every build

Each its own file with its own page: the machines that ran it and their signatures.

buildenginewhose workmemorycontext provedbest tok/smachines
Q8_0 by unslothhf.co/unsloth/Qwen3.5-9B-GGUF:Q8_0ollamaquantizer · unsloth10.6 GB—2.51
Q4_K_M by unslothhf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_Mollamaquantizer · unsloth6.3 GB—2.42
derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSOREDnot measuredQwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTPnot measuredHuihui-Qwen3.5-9B-abliteratednot measuredQwen3.5-9B-Kimi-k3-Distillednot measuredQwen3.5-9B-Artemis-GGUFnot measuredDeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-hereticnot measured