Configs › Muse-Glimmer-30B on Strix Halo: 26.5 tok/s measured
Muse-Glimmer-30B on Strix Halo: 26.5 tok/s measured
Measured Muse-Glimmer-30B speeds: 26.5 tok/s on Strix Halo (FP4, rocm (speculative decode, dflash)). 2 configs, each linked to its source, snapshot 2026-10-30.
Snapshot 2026-10-30 · 412 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 Muse-Glimmer-30B: 26.5 tok/s on Strix Halo (FP4, rocm, speculative decode, dflash), snapshot 2026-10-30.
Fastest measured run on each box
| Hardware | Decode tok/s | Quant | Backend | Context | Trust | Configs on this box | Source |
|---|---|---|---|---|---|---|---|
| Strix Halo | 26.5 | FP4 | rocm (speculative decode, dflash) | Owner-submitted | 2 | source |
Questions and answers
- How fast is Muse-Glimmer-30B on local hardware?
- The fastest measured single-stream run is 26.5 tok/s on Strix Halo (FP4, rocm, speculative decode, dflash). TokenMark tracks 2 single-stream configs for Muse-Glimmer-30B on 1 box.
- How many measured configs does TokenMark have for Muse-Glimmer-30B?
- 2 single-stream configs on 1 box, newest source check 2026-09-16. Every row links to where it was measured.
All measured configs for Muse-Glimmer-30B
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Muse-Glimmer-30B | Strix Halo | FP4 | rocm (speculative decode, dflash) | 26.5 tok/s | Owner-submitted | source | |
| Muse-Glimmer-30B | Strix Halo | FP4 | llama.cpp (speculative decode, dflash) | 20.3 tok/s | 32768 | Extracted, source-linked | source |
Last updated: snapshot 2026-10-30; newest source check 2026-09-16. 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.