Configs › Gemma-4-12B tok/s: Mac Max 56.1, DGX Spark 28.4
Gemma-4-12B tok/s: Mac Max 56.1, DGX Spark 28.4
Measured Gemma-4-12B speeds: 56.1 tok/s on Mac Max (ollama); 28.4 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-4-12B on Mac Max?
- 56.1 tok/s single-stream decode (ollama), the only measured config on Apple M-series Max (MacBook Pro / Mac Studio Max), measured by lizhun781021, source last checked 2026-09-29. source
- How fast is Gemma-4-12B on DGX Spark?
- 28.4 tok/s single-stream decode (Q4_K_M, llama.cpp), the only measured config on NVIDIA DGX Spark (GB10), measured by jvr0x, source last checked 2026-10-15. source
Measured configs for Gemma-4-12B
Also filed as: Gemma-4-12B-IT.
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Gemma-4-12B | Mac Max | ollama | 56.1 tok/s | Extracted, source-linked | source | ||
| Gemma-4-12B-IT | DGX Spark | Q4_K_M | llama.cpp | 28.4 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.