Find edge AI hardware
Task LLM generation · model-size class by model · batch per group · 2 platforms · edge hardware only · model_key "tinyllama11b"
Results are compared only within the same model. 1 model have results for this task.
How to read power: results are compared only within the same model. By efficiency ranks only results whose source publishes a power figure; By speed ranks every result. Measured = measured for this workload. Vendor-measured (typical/avg) = the vendor’s own measurement at typical or average load, not an independent test and not a maximum, so fps/W looks better than at max TDP. Chip, Module or Board TDP = the vendor’s published maximum, not measured. Typical power, not max TDP = only a typical figure is published, so fps/W looks better than at full load. Scope says what the watts cover: Accelerator only (host not included), Module, or Whole system. Max of range = top of a published range, so fps/W is a floor (≥). “— not published” = the source gives no power; we never estimate one.
TinyLlama 1.1B 2 platforms · 0 with published power
| Rank | Platform | tok/s/W | tok/s | Power | Model · precision · batch | Grade · date | Source |
|---|---|---|---|---|---|---|---|
| – | AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | ≥2.08Chip TDP · Accelerator only · floor | 249 tok/s | 120 WAccelerator only, host not includedChip TDP · max of range 45-120 W | TinyLlama 1.1BQ4_K_M · batch 1 | C 2026-03-03 (published) | visorcraft/strix-halo-llm-perf README (single-host table)README @ ad33379 |
| – | Dell Optiplex 780 (Intel Core 2 Quad Q8400) (as tested by Jeff Geerling) | 4.04 tok/s | — not published | tinyllama:1.1bOllama default tag (4-bit unless tag says otherwise) · batch 1 | C 2025-11-05 (page last edited) | Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19 |
| Rank | Platform | tok/s/W | tok/s | Power | Model · precision · batch | Grade · date | Source |
|---|---|---|---|---|---|---|---|
| 1 | AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | ≥2.08Chip TDP · Accelerator only · floor | 249 tok/s | 120 WAccelerator only, host not includedChip TDP · max of range 45-120 W | TinyLlama 1.1BQ4_K_M · batch 1 | C 2026-03-03 (published) | visorcraft/strix-halo-llm-perf README (single-host table)README @ ad33379 |
| 2 | Dell Optiplex 780 (Intel Core 2 Quad Q8400) (as tested by Jeff Geerling) | 4.04 tok/s | — not published | tinyllama:1.1bOllama default tag (4-bit unless tag says otherwise) · batch 1 | C 2025-11-05 (page last edited) | Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19 |
Excluded from ranking (1)
Partial or suspected partial models, fps/W outliers and rows HWBench Data flags (rank_note) are kept out of the rankings. Rows with a published power figure that Data does not mark for the default fps/W ranking still appear under By speed. Every row stays in /find.json.
| Platform | Model | Result | Power | Left out of | Why | Source |
|---|---|---|---|---|---|---|
| AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | TinyLlama 1.1B | 249 tok/s | 120 WAccelerator only, host not includedChip TDP · max of range 45-120 W | Efficiency ranking | HWBench Data has not verified tok/s/W rows for ranking yet | visorcraft/strix-halo-llm-perf README (single-host table)README @ ad33379 |