Configs › Flint on Strix Halo: 56.8 tok/s measured
Flint on Strix Halo: 56.8 tok/s measured
Measured Flint speeds: 56.8 tok/s on Strix Halo (UD-Q4_K_XL, llama.cpp/vulkan). 1 config, each linked to its source, snapshot 2026-10-29.
Snapshot 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Fastest measured single-stream run of Flint: 56.8 tok/s on Strix Halo (UD-Q4_K_XL, llama.cpp/vulkan), snapshot 2026-10-29.
Fastest measured run on each box
| Hardware | Decode tok/s | Quant | Backend | Context | Trust | Configs on this box | Source |
|---|---|---|---|---|---|---|---|
| Strix Halo | 56.8 | UD-Q4_K_XL | llama.cpp/vulkan | 65536 | Extracted, source-linked | 1 | source |
Questions and answers
- How fast is Flint on local hardware?
- The fastest measured single-stream run is 56.8 tok/s on Strix Halo (UD-Q4_K_XL, llama.cpp/vulkan). TokenMark tracks 1 single-stream config for Flint on 1 box.
- How many measured configs does TokenMark have for Flint?
- 1 single-stream config on 1 box, newest source check 2026-10-24. Every row links to where it was measured.
All measured configs for Flint
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Flint | Strix Halo | UD-Q4_K_XL | llama.cpp/vulkan | 56.8 tok/s (prefill 1451) | 65536 | Extracted, source-linked | source |
Last updated: snapshot 2026-10-29; newest source check 2026-10-24. Rankings use single-stream runs only; aggregate and multi-GPU rows are kept off them.
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.