Multi-GPU x3

Other · 72 GB VRAM

4recorded runs

63.3best tok/s

0sourced

Evidence: 0 sourced runs · 4 awaiting review · 1 independent source · first recorded Aug 8, 2026 · last recorded Aug 8, 2026. What these labels mean.

What fits on 72 GB — measured

Model	Quant	Peak VRAM	Headroom
Ling-3.0-flash	AD-IQ4_XXS	68.4 GB	3.6 GB
Qwen3.6-35B-A3B	APEX-I-Balanced	65.7 GB	6.3 GB
Laguna-S-2.1	UD-IQ4_XS	65.1 GB	6.9 GB
Qwen3.6-27B	Q6_K_L	51.4 GB	20.6 GB

Peak process memory recorded by the submitter on this card — evidence of what fit, not a guarantee. Plan with the VRAM calculator.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Multi-GPU x3 · 72 GB	Qwen3.6-35B-A3B	APEX-I-Balanced	llama.cpp 81 (15586e2)	2097152	63.3 …	—	65.7	src
Multi-GPU x3 · 72 GB	Qwen3.6-27B	Q6_K_L	llama.cpp 81 (15586e2)	524288	60.3 …	—	51.4	src
Multi-GPU x3 · 72 GB	Ling-3.0-flash	AD-IQ4_XXS	llama.cpp b10269-1.5.1 (build 10696, commit cd…	262144	43.4 …	—	68.4	src
Multi-GPU x3 · 72 GB	Laguna-S-2.1	UD-IQ4_XS	llama.cpp 81 (15586e2)	278528	23.9 …	—	65.1	src