family member
Qwen 3 logo

Qwen3-VL-8B-Instruct-abliterated-v1

1 build of Qwen3-VL-8B-Instruct-abliterated-v1, 3 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.

22tok/s, fastest machine
4Kcontext proved by recall
3.7 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 Qwen3-VL-8B-Instruct-abliterated-v1 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 · 1 build

proved 4K context, by mradermacher Q2_K

22.4 tok/s peak, by mradermacher Q2_K

Same build, different machines

Q2_K by mradermacher on 3 machines: the fastest decodes 9.6× as fast as the slowest. One dot per machine, tokens per second.

  1. Apple M4×122 tok/s
  2. Intel(R) Iris(R) Xe Graphics×13.8 tok/s
  3. Intel(R) UHD Graphics 730×12.3 tok/s

What it fits on

The smallest build needs about 3.7 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 cardevery build
  3. NVIDIA GeForce GTX 16504 GB on the cardevery build
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMevery build
  5. Windows, CPU only · 12 CPUs7 GB RAMevery build
  6. Apple silicon8 GB RAMevery build
  7. Apple M18 GB RAMevery build
  8. Mac, CPU only · 8 CPUs8 GB RAMevery build
  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

How far back it remembers, machine by machine

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

machine · build4Kwhy it stopped
Gram ·afbb8aApple M4 · Q2_K by mradermacher4K an older probe: where it stopped was not recorded
Gram ·2e5c02Intel(R) Iris(R) Xe Graphics · Q2_K by mradermacher— an older probe: where it stopped was not recorded
Gram ·9e3c79Intel(R) UHD Graphics 730 · Q2_K by mradermacher— an older probe: where it stopped was not recorded

Measured by

The people whose machines signed these numbers

proved by at least one build: Tool calling · Tool loop finished · Structured output · Sustained output · Vision · Counts in images · 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
Q2_K by mradermacherhf.co/mradermacher/Qwen3-VL-8B-Instruct-abliterated-GGUF:Q2_Ksafety removedollamaderivative · mradermacher3.7 GB4K22.43