community pool / model answer

Qwen3.5-35B-A3B-GGUF

chat · unsloth/Qwen3.5-35B-A3B-GGUF

60.3 tok/s · model median · 5 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
GB10 Grace Blackwell 128GB	4-bit	60.3 tok/s	reported	-	- GB	262,144	llama.cpp
GB10 Grace Blackwell 128GB	8-bit	35.1 tok/s	reported	-	- GB	262,144	llama.cpp
Minisforum UM790 Pro 64GB	4-bit	23.6 tok/s	reported	-	- GB	2,048	llama.cpp
RTX 3090 24GB	4-bit	124.4 tok/s	reported	-	- GB	2,048	llama.cpp
RTX 4090 24GB	4-bit	157.4 tok/s	reported	-	- GB	2,048	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.