community pool / model answer

Ornith-1.0-9B-GGUF

chat · deepreinforce-ai/Ornith-1.0-9B-GGUF

34.3 tok/s · model median · 31 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
RX 570 4GB	4-bit	22.5 tok/s	measured	286	- GB	2,048	llama.cpp
RX 570 4GB ×2	4-bit	55.7 tok/s	measured	294	- GB	2,048	llama.cpp
RX 5700 4GB	4-bit	27.4 tok/s	reported	129	- GB	2,048	llama.cpp
RX 5700 8GB	4-bit	27.4 tok/s	reported	131	- GB	2,048	llama.cpp
Ryzen AI Max 395 128GB	5-bit	31.8 tok/s	reported	146	6.9 GB	4,096	llama.cpp
Ryzen AI Max 395 64GB	4-bit	35.5 tok/s	reported	1,753	6.3 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.