family member
Qwen 3 logo

Qwen 3 VL-4B

12 tokens a second on Linux · NVIDIA 15 GB · 4 CPUs · 31 GB RAM. No hosted API sells it, so this network is the place to run it.

1 build of Qwen 3 VL-4B, 1 signed run on real machines: different packagers, precisions and engines, each a different file with its own numbers.

12tok/s, fastest machine
$12per M tokens · no API sells it
128Kcontext proved by recall
33.9 GBmemory, smallest build
1provider 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. 1 provider has measured Qwen 3 VL-4B so far.Use it in your own room Ask Evo in your gramx and it runs on a machine that proved it, at the metered $12 per million tokens. 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 · 1 build

trained 256K · proved 128K context, by Qwen F16

12.2 tok/s peak, by Qwen F16

What it fits on

The smallest build needs about 33.9 GB; 1 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 RAMnone
  5. Windows, CPU only · 12 CPUs7 GB RAMnone
  6. Apple silicon8 GB RAMnone
  7. Apple M18 GB RAMnone
  8. Mac, CPU only · 8 CPUs8 GB RAMnone
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the cardnone
  10. Tesla T415 GB on the cardnone
  11. Intel(R) UHD Graphics 73016 GB RAMnone
  12. Intel(R) Iris(R) Xe Graphics16 GB RAMnone
  13. Apple M416 GB RAMnone
  14. Apple M116 GB RAMnone
  15. NVIDIA L422 GB on the cardnone
  16. 2× Tesla T429 GB on the cardnone
  17. Linux, CPU only · 4 CPUs31 GB RAMnone
  18. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery build

How far back it remembers, machine by machine

Filled: the needle came back at that prompt size · outlined: asked and lost · blank: not asked · trained for 256K. 0 walks ended because the model forgot, 0 because the machine could not hold the prompt.

machine · build4K8K16K32K64K128Kwhy it stopped
Gram ·a5be462× Tesla T4 · F16 by Qwen128K recalled at every size asked

Measured by

The people whose machines signed these numbers

proved by at least one build: Tool calling · Faithful to tool results · Structured output · Sustained output · Vision · Counts in images · Multiple images at once · Spatial reasoning · Writes code · Follows instructions

Every build

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

buildenginewhose workmemorycontext provedbest tok/smachines
F16 by Qwenhf.co/Qwen/Qwen3-VL-4B-Instruct-GGUF:F16ollamavendor · Qwen33.9 GB128K12.21