Radeon AI PRO R9700

96 records across 11 models (quants: EXL3 3.05 bpw, EXL3 4.05 bpw, FP8, Gyro-S, IQ4_XS, MXFP4, Q2_K, Q4_0, Q4_K, Q4_K_M, Q5_K_P, Q8_0, UD-Q4_K_XL, as-published).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
Radeon AI PRO R9700Gemma 4 12B FP8vLLM32.7––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM32.62––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM31.41––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM31.38––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM28.8––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM28.59––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM28.09––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM28.09––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM26.82––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM26.64––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM24.79––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM24.57––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM23.91––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM23.6––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM20.88––––2026-10-11sourced–source
Radeon AI PRO R9700Gemma 4 12B FP8vLLM20.65––––2026-10-11sourced–source
Radeon AI PRO R9700gemma-4-12b-it FP8vLLM33.38––––2026-10-06community–source
Radeon AI PRO R9700gemma-4-12b-it FP8vLLM–1102–––2026-10-06community–source
Radeon AI PRO R9700llama 7B Q4_0llama.cpp (Vulkan)131.195411.28––tg1282026-09-12community–source
Radeon AI PRO R9700llama 7B Q4_0llama.cpp (Vulkan)130.974235.87––tg1282026-09-12community–source
Radeon AI PRO R9700llama 7B Q4_0llama.cpp (Vulkan)125.965033.0––tg1282026-09-12community–source
Radeon AI PRO R9700llama 7B Q4_0llama.cpp (ROCm)121.625039.78––tg1282026-09-12community–source
Radeon AI PRO R9700llama 7B Q4_0llama.cpp (ROCm)121.292755.01––tg1282026-09-12community–source
Radeon AI PRO R9700llama 7B Q4_0llama.cpp (ROCm)112.724665.08––tg1282026-09-12community–source
Radeon AI PRO R9700Mistral Small 4 IQ4_XSllama.cpp (Vulkan)31.56–––1282026-10-07community–source
Radeon AI PRO R9700Mistral Small 4 IQ4_XSllama.cpp (Vulkan)2.99–––1282026-10-07community–source
Radeon AI PRO R9700Mistral Small 4 IQ4_XSllama.cpp (Vulkan)–242.75––5122026-10-07community–source
Radeon AI PRO R9700Mistral Small 4 IQ4_XSllama.cpp (Vulkan)–240.0––5122026-10-07community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM48.9––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM48.2––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM46.6––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM46.5––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM42.2––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM37.2––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM36.2––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM35.9––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM35.9––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM35.8––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM34.3––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM33––––2026-09-27community–source
Radeon AI PRO R9700MoE hybrid model as-publishedvLLM31.0––––2026-09-27community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)115.4–––20482026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)112.3–––81922026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)101.4–––327682026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)90.7–––655362026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)81.9–––983042026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)75.3–––1310722026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)–4014––20482026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)–4487––81922026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)–3872––327682026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)–3173––655362026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)–2667––983042026-10-17community–source
Radeon AI PRO R9700Ornith-1.5-35B-A3B MXFP4llama.cpp (ROCm)–2307––1310722026-10-17community–source
Radeon AI PRO R9700Qwen3.8-27B 27BUD-Q4_K_XLllama.cpp (ROCm)51.70––––2026-09community–source
Radeon AI PRO R9700Qwen3.8-27B 27BUD-Q4_K_XLllama.cpp (ROCm)51.69––––2026-09community–source
Radeon AI PRO R9700Qwen3.8-27B 27BUD-Q4_K_XLllama.cpp (ROCm)51.62––––2026-09community–source
Radeon AI PRO R9700Qwen3.8-27B 27BUD-Q4_K_XLllama.cpp (ROCm)51.37––––2026-09community–source
Radeon AI PRO R9700Qwen3.8-27B 27BUD-Q4_K_XLllama.cpp (ROCm)41.37––––2026-09community–source
Radeon AI PRO R9700Qwen3.8-27B 27BUD-Q4_K_XLllama.cpp (ROCm)40.96––––2026-09community–source
Radeon AI PRO R9700Qwen3.8-27B Q2_Kllama.cpp (ROCm)–471.2–––2026-08community–source
Radeon AI PRO R9700Qwen3.8-27B Q4_Kllama.cpp (ROCm)–1120.7–––2026-08community–source
Radeon AI PRO R9700Qwen3.8-27B Q8_0llama.cpp (ROCm)–1178.3–––2026-08community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next agentionai/llama.cpp Vulkan build (rotor formats), llama-bench batch 1, no draftingGyro-Sllama.cpp (Vulkan)70.6––––2026-10-02community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 3.05 bpwranma.cpp (ROCm)60.8–––655362026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 3.05 bpwranma.cpp (ROCm)58.8–––655362026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next agentionai/llama.cpp Vulkan build (rotor formats), llama-bench batch 1, no draftingGyro-Sllama.cpp (Vulkan)57.81246––tg1282026-10-02community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 4.05 bpwranma.cpp (ROCm)53.9–––655362026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 3.05 bpwranma.cpp (ROCm)53.5–––tg1282026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 4.05 bpwranma.cpp (ROCm)53.3–––655362026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 3.05 bpwranma.cpp (ROCm)52.4–––tg1282026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 4.05 bpwranma.cpp (ROCm)49.6–––tg1282026-10-05community–source
Radeon AI PRO R9700Qwen3.8-Flash-Next 80B-A3BEXL3 4.05 bpwranma.cpp (ROCm)47.7–––tg1282026-10-05community–source
Radeon AI PRO R9700qwen35 dense 27B 27BQ5_K_Pllama.cpp (Vulkan)60630––500002026-08community–source
Radeon AI PRO R9700qwen35 dense 27B 27BQ5_K_Pllama.cpp (Vulkan)53594––500002026-08community–source
Radeon AI PRO R9700qwen35 dense 27B 27BQ5_K_Pllama.cpp (Vulkan)50641––500002026-08community–source
Radeon AI PRO R9700qwen35 dense 27B 27BQ5_K_Pllama.cpp (Vulkan)9.536––500002026-08community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp174.6–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp174.5–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp127.3–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp104.9–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp91.8–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp88.6–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp84.4–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp81.1–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp77.0–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp75.9–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp50.9–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp50.6–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp29.5–––327682026-10-01community–source
Radeon AI PRO R9700Qwopus3.8-27B-Flash-V2 Q4_K_Mllama.cpp29.4–––327682026-10-01community–source
Radeon AI PRO R9700Swift 1.5 MXFP4llama.cpp (ROCm)60.7––––2026-10-03community–source
Radeon AI PRO R9700Swift 1.5 MXFP4llama.cpp (ROCm)58.1––––2026-10-03community–source
Radeon AI PRO R9700Swift 1.5 MXFP4llama.cpp (ROCm)55.9––––2026-10-03community–source
Radeon AI PRO R9700Swift 1.5 MXFP4llama.cpp (ROCm)33.81206–––2026-10-03community–source
Radeon AI PRO R9700Swift 1.5 MXFP4llama.cpp (ROCm)33.31215–––2026-10-03community–source
Radeon AI PRO R9700Swift 1.5 MXFP4llama.cpp (ROCm)32.81212–––2026-10-03community–source

All rows cite their source. Provenance: community 40018 sourced 1085

← all hardware