Configs › K2-Think-V2 on DGX Spark: 3.2 tok/s measured
K2-Think-V2 on DGX Spark: 3.2 tok/s measured
Measured K2-Think-V2 speeds: 3.2 tok/s on DGX Spark (Q6_K, llama.cpp). 1 config, 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 K2-Think-V2 on DGX Spark?
- 3.2 tok/s single-stream decode (Q6_K, llama.cpp), the only measured config on NVIDIA DGX Spark (GB10), measured by cuber-1, source last checked 2026-09-20. source
Measured configs for K2-Think-V2
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| K2-Think-V2 | DGX Spark | Q6_K | llama.cpp | 3.2 tok/s | Extracted, source-linked | 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.