3 builds of Phi 4 REASONING-PLUS measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it.
trained 32K · proved 32K context proved by unsloth Q4_K_M
24.5 tok/s peak, by unsloth Q4_K_M
proved by at least one build: Structured output · Sustained output · Reasons about code · Synthesises sources · Follows instructions
| build | publisher | precision | engine | whose work | context proved | best tok/s | machines |
|---|---|---|---|---|---|---|---|
| hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q4_K_M | unsloth | Q4_K_M | ollama | quantizer | 32,768 | 24.5 | 1 |
| hf.co/lmstudio-community/Phi-4-reasoning-plus-GGUF:Q6_K | lmstudio-community | Q6_K | ollama | — | — | 3.3 | 1 |
| hf.co/lmstudio-community/Phi-4-reasoning-plus-GGUF:Q4_K_M | lmstudio-community | Q4_K_M | ollama | — | — | — | 1 |