community pool / model answer

Ornith-1.0-35B

chat · ornith-ai/Ornith-1.0-35B

71.8 tok/s · model median · 12 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
Arc Pro B70 32GB	4-bit	74.3 tok/s	reported	73	- GB	262,144	llama.cpp
Arc Pro B70 32GB	5-bit	69.3 tok/s	measured	-	- GB	262,144	llama.cpp
M3 Ultra 512GB	4-bit	89.1 tok/s	reported	111	- GB	8,192	llama.cpp
Radeon AI Pro R9700 32GB ×3	8-bit	74 tok/s	reported	366	42.9 GB	787	llama.cpp
Ryzen AI Max 395 128GB	8-bit	54.1 tok/s	reported	1,244	- GB	787	llama.cpp
Ryzen AI Max 395 64GB	4-bit	60.6 tok/s	measured	970	21.4 GB	8,192	llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.