Configs › Gemma-4-31B tok/s: Mac Ultra 13.6, DGX Spark 6.6
Gemma-4-31B tok/s: Mac Ultra 13.6, DGX Spark 6.6
Measured Gemma-4-31B speeds: 13.6 tok/s on Mac Ultra (BF16, mlx); 6.6 tok/s on DGX Spark. 2 configs, each linked to its source, snapshot 2026-10-15.
Snapshot 2026-10-15 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Quick answers
- How fast is Gemma-4-31B on Mac Ultra?
- 13.6 tok/s single-stream decode (BF16, mlx), the only measured config on Apple Mac Studio (M-series Ultra), measured by theNetworkChuck, source last checked 2026-09-29. source
- How fast is Gemma-4-31B on DGX Spark?
- 6.6 tok/s single-stream decode (NVFP4, vllm), the only measured config on NVIDIA DGX Spark (GB10), measured by jvr0x, source last checked 2026-10-15. source
Measured configs for Gemma-4-31B
Also filed as: Gemma-4-31B-IT.
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Gemma-4-31B | Mac Ultra | BF16 | mlx | 13.6 tok/s (prefill 1217) | 32000 | Extracted, source-linked | source |
| Gemma-4-31B-IT | DGX Spark | NVFP4 | vllm | 6.6 tok/s | Structured table | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.