Radeon AI Pro R9700 x3

Amd · 32 GB VRAM

10recorded runs

250.6best tok/s

9sourced

How it compares — 32 GB per card · multi-GPU

Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.

Evidence: 9 sourced runs · 1 awaiting review · 1 independent source · first recorded May 5, 2026 · last recorded Sep 4, 2026. What these labels mean.

Model	Quant	Peak VRAM	Headroom
Ornith-1.0-9B	BF16	25.8 GB	6.2 GB
Qwen3-VL-8B-Instruct	Q8_0	15.5 GB	16.5 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
Radeon AI Pro R9700 x3 · 32 GB	gpt-oss-120b	MXFP4	vllm 0.20.2+rocm-mxfp4-docker	32768	223.4 ✓	—	—	src
Radeon AI Pro R9700 x3 · 32 GB	Nemotron-Cascade-2-30B-A3B	Q8_0	llama.cpp b9025-1-ga267d945e	812	95.4 ✓	—	—	src
Radeon AI Pro R9700 x3 · 32 GB	Qwen3-VL-8B-Instruct	Q8_0	llama.cpp b10107	786	58.8 ✓	3037.9	15.5	src
Radeon AI Pro R9700 x3 · 32 GB	Muse-Glimmer-30B	UD-Q8_K_XL	llama.cpp b10434	834	47.8 ✓	787.5	—	src
Radeon AI Pro R9700 x3 · 32 GB	Ling-3.0-flash	Q4_0_ROCMFP4_STRIX_LEAN	llama.cpp ROCmFPX db6844d + BailingMoe3 port	4096	39.3 ✓	542.6	—	src
Radeon AI Pro R9700 x3 · 32 GB	Ornith-1.5-35B-A3B	BF16	llama.cpp b10679-50f068fff	262144	35.4 ✓	1454.2	—	src
Radeon AI Pro R9700 x3 · 32 GB	Ornith-1.0-9B	BF16	llama.cpp b10107	787	31.2 ✓	1631.6	25.8	src
Radeon AI Pro R9700 x3 · 32 GB	Qwen3.8-Flash-Next	UD-IQ3_XXS	llama.cpp b10643-11-gaecd368d0	829	28.1 ✓	474.4	—	src
Radeon AI Pro R9700 x3 · 32 GB	gemma-4-31B-it	Q8_0	llama.cpp b10434	794	23.9 ✓	597.3	—	src
Radeon AI Pro R9700 x3 · 32 GB	GLM-5.3-Flash	compressed-tensors	sglang —	12000	250.6 …	3482.2	—	src