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).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 32.7 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 32.62 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 31.41 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 31.38 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 28.8 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 28.59 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 28.09 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 28.09 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 26.82 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 26.64 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 24.79 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 24.57 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 23.91 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 23.6 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 20.88 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | Gemma 4 12B | FP8 | vLLM | 20.65 | – | – | – | – | 2026-10-11 | sourced | – | source |
| Radeon AI PRO R9700 | gemma-4-12b-it | FP8 | vLLM | 33.38 | – | – | – | – | 2026-10-06 | community | – | source |
| Radeon AI PRO R9700 | gemma-4-12b-it | FP8 | vLLM | – | 1102 | – | – | – | 2026-10-06 | community | – | source |
| Radeon AI PRO R9700 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 131.19 | 5411.28 | – | – | tg128 | 2026-09-12 | community | – | source |
| Radeon AI PRO R9700 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 130.97 | 4235.87 | – | – | tg128 | 2026-09-12 | community | – | source |
| Radeon AI PRO R9700 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 125.96 | 5033.0 | – | – | tg128 | 2026-09-12 | community | – | source |
| Radeon AI PRO R9700 | llama 7B | Q4_0 | llama.cpp (ROCm) | 121.62 | 5039.78 | – | – | tg128 | 2026-09-12 | community | – | source |
| Radeon AI PRO R9700 | llama 7B | Q4_0 | llama.cpp (ROCm) | 121.29 | 2755.01 | – | – | tg128 | 2026-09-12 | community | – | source |
| Radeon AI PRO R9700 | llama 7B | Q4_0 | llama.cpp (ROCm) | 112.72 | 4665.08 | – | – | tg128 | 2026-09-12 | community | – | source |
| Radeon AI PRO R9700 | Mistral Small 4 | IQ4_XS | llama.cpp (Vulkan) | 31.56 | – | – | – | 128 | 2026-10-07 | community | – | source |
| Radeon AI PRO R9700 | Mistral Small 4 | IQ4_XS | llama.cpp (Vulkan) | 2.99 | – | – | – | 128 | 2026-10-07 | community | – | source |
| Radeon AI PRO R9700 | Mistral Small 4 | IQ4_XS | llama.cpp (Vulkan) | – | 242.75 | – | – | 512 | 2026-10-07 | community | – | source |
| Radeon AI PRO R9700 | Mistral Small 4 | IQ4_XS | llama.cpp (Vulkan) | – | 240.0 | – | – | 512 | 2026-10-07 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 48.9 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 48.2 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 46.6 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 46.5 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 42.2 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 37.2 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 36.2 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 35.9 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 35.9 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 35.8 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 34.3 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 33 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | MoE hybrid model | as-published | vLLM | 31.0 | – | – | – | – | 2026-09-27 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | 115.4 | – | – | – | 2048 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | 112.3 | – | – | – | 8192 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | 101.4 | – | – | – | 32768 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | 90.7 | – | – | – | 65536 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | 81.9 | – | – | – | 98304 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | 75.3 | – | – | – | 131072 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | – | 4014 | – | – | 2048 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | – | 4487 | – | – | 8192 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | – | 3872 | – | – | 32768 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | – | 3173 | – | – | 65536 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | – | 2667 | – | – | 98304 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Ornith-1.5-35B-A3B | MXFP4 | llama.cpp (ROCm) | – | 2307 | – | – | 131072 | 2026-10-17 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B 27B | UD-Q4_K_XL | llama.cpp (ROCm) | 51.70 | – | – | – | – | 2026-09 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B 27B | UD-Q4_K_XL | llama.cpp (ROCm) | 51.69 | – | – | – | – | 2026-09 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B 27B | UD-Q4_K_XL | llama.cpp (ROCm) | 51.62 | – | – | – | – | 2026-09 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B 27B | UD-Q4_K_XL | llama.cpp (ROCm) | 51.37 | – | – | – | – | 2026-09 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B 27B | UD-Q4_K_XL | llama.cpp (ROCm) | 41.37 | – | – | – | – | 2026-09 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B 27B | UD-Q4_K_XL | llama.cpp (ROCm) | 40.96 | – | – | – | – | 2026-09 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B | Q2_K | llama.cpp (ROCm) | – | 471.2 | – | – | – | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B | Q4_K | llama.cpp (ROCm) | – | 1120.7 | – | – | – | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-27B | Q8_0 | llama.cpp (ROCm) | – | 1178.3 | – | – | – | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next agentionai/llama.cpp Vulkan build (rotor formats), llama-bench batch 1, no drafting | Gyro-S | llama.cpp (Vulkan) | 70.6 | – | – | – | – | 2026-10-02 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 3.05 bpw | ranma.cpp (ROCm) | 60.8 | – | – | – | 65536 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 3.05 bpw | ranma.cpp (ROCm) | 58.8 | – | – | – | 65536 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next agentionai/llama.cpp Vulkan build (rotor formats), llama-bench batch 1, no drafting | Gyro-S | llama.cpp (Vulkan) | 57.8 | 1246 | – | – | tg128 | 2026-10-02 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 4.05 bpw | ranma.cpp (ROCm) | 53.9 | – | – | – | 65536 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 3.05 bpw | ranma.cpp (ROCm) | 53.5 | – | – | – | tg128 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 4.05 bpw | ranma.cpp (ROCm) | 53.3 | – | – | – | 65536 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 3.05 bpw | ranma.cpp (ROCm) | 52.4 | – | – | – | tg128 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 4.05 bpw | ranma.cpp (ROCm) | 49.6 | – | – | – | tg128 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | Qwen3.8-Flash-Next 80B-A3B | EXL3 4.05 bpw | ranma.cpp (ROCm) | 47.7 | – | – | – | tg128 | 2026-10-05 | community | – | source |
| Radeon AI PRO R9700 | qwen35 dense 27B 27B | Q5_K_P | llama.cpp (Vulkan) | 60 | 630 | – | – | 50000 | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | qwen35 dense 27B 27B | Q5_K_P | llama.cpp (Vulkan) | 53 | 594 | – | – | 50000 | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | qwen35 dense 27B 27B | Q5_K_P | llama.cpp (Vulkan) | 50 | 641 | – | – | 50000 | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | qwen35 dense 27B 27B | Q5_K_P | llama.cpp (Vulkan) | 9.5 | 36 | – | – | 50000 | 2026-08 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 174.6 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 174.5 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 127.3 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 104.9 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 91.8 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 88.6 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 84.4 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 81.1 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 77.0 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 75.9 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 50.9 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 50.6 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 29.5 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Qwopus3.8-27B-Flash-V2 | Q4_K_M | llama.cpp | 29.4 | – | – | – | 32768 | 2026-10-01 | community | – | source |
| Radeon AI PRO R9700 | Swift 1.5 | MXFP4 | llama.cpp (ROCm) | 60.7 | – | – | – | – | 2026-10-03 | community | – | source |
| Radeon AI PRO R9700 | Swift 1.5 | MXFP4 | llama.cpp (ROCm) | 58.1 | – | – | – | – | 2026-10-03 | community | – | source |
| Radeon AI PRO R9700 | Swift 1.5 | MXFP4 | llama.cpp (ROCm) | 55.9 | – | – | – | – | 2026-10-03 | community | – | source |
| Radeon AI PRO R9700 | Swift 1.5 | MXFP4 | llama.cpp (ROCm) | 33.8 | 1206 | – | – | – | 2026-10-03 | community | – | source |
| Radeon AI PRO R9700 | Swift 1.5 | MXFP4 | llama.cpp (ROCm) | 33.3 | 1215 | – | – | – | 2026-10-03 | community | – | source |
| Radeon AI PRO R9700 | Swift 1.5 | MXFP4 | llama.cpp (ROCm) | 32.8 | 1212 | – | – | – | 2026-10-03 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085