RTX PRO 6000 Blackwell

Nvidia · 96 GB VRAM

32recorded runs

1271.3best tok/s

29sourced

Evidence: 29 sourced runs · 3 awaiting review · 1 independent source · first recorded Jul 1, 2026 · last recorded Sep 4, 2026. What these labels mean.

What fits on 96 GB — measured

Model	Quant	Peak VRAM	Headroom
Ornith-1.0-35B	Q4_K_M	72.7 GB	23.3 GB
Muse-Glimmer-30B	BF16	52.3 GB	43.7 GB
Muse-Glimmer-30B	Q8_K_XL	32.8 GB	63.2 GB
Llama-3.2-3B-Instruct	Q4_K_M	2.6 GB	93.4 GB
Llama-3.2-1B-Instruct	Q8_0	2.1 GB	93.9 GB
gemma-3-1b-it	Q4_K_M	1.9 GB	94.1 GB
Qwen2.5-0.5B-Instruct	Q8_0	1.8 GB	94.2 GB
SmolLM2-360M-Instruct	Q8_0	1.1 GB	94.9 GB

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

All benchmarks Compare RTX PRO 6000 Blackwell →

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX PRO 6000 Blackwell · 96 GB	MobileLLM-125M	Q8_0	llama.cpp 876a432	4608	1271.3 ✓	138696.6	1.0	src
RTX PRO 6000 Blackwell · 96 GB	Qwen2.5-0.5B-Instruct	Q8_0	llama.cpp 876a432	4608	1060.0 ✓	116339.6	1.8	src
RTX PRO 6000 Blackwell · 96 GB	MobileLLM-350M	Q8_0	llama.cpp 876a432	4608	980.8 ✓	103262.6	1.0	src
RTX PRO 6000 Blackwell · 96 GB	SmolLM2-360M-Instruct	Q8_0	llama.cpp 876a432	4608	968.1 ✓	103783.1	1.1	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3-0.6B	Q4_K_M	llama.cpp 876a432	640	956.4 ✓	57064.9	1.1	src
RTX PRO 6000 Blackwell · 96 GB	Llama-3.2-1B-Instruct	Q8_0	llama.cpp 876a432	4096	699.9 ✓	64851.3	2.1	src
RTX PRO 6000 Blackwell · 96 GB	gemma-3-1b-it	Q4_K_M	llama.cpp 876a432	640	664.3 ✓	45428.7	1.9	src
RTX PRO 6000 Blackwell · 96 GB	Llama-3.2-3B-Instruct	Q4_K_M	llama.cpp 876a432	640	489.2 ✓	28478.5	2.6	src
RTX PRO 6000 Blackwell · 96 GB	Ling-3.0-tiny	Q4_K_M	llama.cpp 966ea60e1	640	369.1 ✓	20069.5	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.6-35B-A3B	NVFP4	vllm 0.26.0	262144	330.2 ✓	11518.9	—	src
RTX PRO 6000 Blackwell · 96 GB	Ornith-1.0-35B	Q4_K_M	llama.cpp v1 (6f4f53f)	524288	309.7 ✓	8996.0	72.7	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B	NVFP4	sglang dev-qwen38-27b-dflash2	262144	296.0 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	DeepSeek-Coder-V2-Lite-Instruct	FP8	vllm 0.26.0	32768	237.3 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3-Coder-Next	FP8	vllm 0.26.0	32768	174.3 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Llama-3.1-8B-Instruct	FP8	vllm 0.26.0	32768	158.1 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Muse-Glimmer-30B	NVFP4	vllm 0.1.dev1+g075d645af	32768	152.2 ✓	4396.9	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B-MTP	NVFP4	vllm 0.27.1	2048	112.1 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Muse-Glimmer-30B	FP8	vllm 0.1.dev1+g075d645af	32768	106.6 ✓	7584.4	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.6-27B	FP8	vllm 0.26.0	131072	101.4 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B	FP8	vllm 0.26.0	131072	101.4 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3-14B	FP8	vllm 0.26.0	32768	90.8 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Kimi-Linear-48B-A3B-Instruct	Q8_0	llama.cpp 10355	1000000	90.0 ✓	732.4	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B	Q8_K_XL	llama.cpp 0.1.2-dev build 10498	99100	88.1 ✓	2311.4	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.6-27B	NVFP4	vllm 0.26.0	131072	73.0 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.6-27B-MTP	Q6_K	llama.cpp 10355	131072	60.1 ✓	1856.7	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen2.5-Coder-14B-Instruct	BF16	vllm 0.26.0	32768	50.3 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Muse-Glimmer-30B	Q8_K_XL	llama.cpp 10355	131072	48.1 ✓	3624.0	32.8	src
RTX PRO 6000 Blackwell · 96 GB	Muse-Glimmer-30B	BF16	llama.cpp 10355	131072	28.8 ✓	3665.0	52.3	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3-Coder-30B-A3B-Instruct	FP8	vllm 0.26.0	32768	26.1 ✓	—	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B	NVFP4	llama.cpp —	2048	120.6 …	351.0	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B	NVFP4	sglang —	2048	97.4 …	1828.6	—	src
RTX PRO 6000 Blackwell · 96 GB	Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP	NVFP4-mixed	llama.cpp —	2048	76.7 …	5835.4	—	src

Related reading: GPU buying guide · used GPUs · Value index · Street prices