Radeon AI Pro R9700
20recorded runs
969.4best tok/s
14sourced
How it compares — 32 GB tier
What fits on 32 GB — measured
| Model | Quant | Peak VRAM | Headroom |
|---|---|---|---|
| GLM-5.3-Flash | UD-IQ1_M | 92.2 GB | -60.2 GB |
| Qwen3.8-Flash-Next | IQ4_XS | 32.9 GB | -0.9 GB |
| DeepSeek-V4-Flash-0731 | IQ2_XXS | 25.2 GB | 6.8 GB |
| Muse-Glimmer-30B | Dynamic-Q4_K_XL + DFlash2-Q4_K_M | 23.6 GB | 8.4 GB |
| Qwen3.5-27B | MQ4-AWQ | 17.5 GB | 14.5 GB |
| LFM2.5-8B-A1B | MQ4 | 5.4 GB | 26.6 GB |
All benchmarks Compare Radeon AI Pro R9700 →
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| Radeon AI Pro R9700 · 32 GB | Qwen3.6-35B-A3B | MQ4R | hipfire 0.3.0+b0bcc3f91506 | 4096 | 969.4 ✓ | — | — | src |
| Radeon AI Pro R9700 · 32 GB | Qwen3.5-0.8B | MQ4 | hipfire 0.3.0+44eb828cc804 | 128 | 554.5 ✓ | — | — | src |
| Radeon AI Pro R9700 · 32 GB | LFM2.5-230M | MQ4 | hipfire 0.3.0+439233d92959 | 4096 | 520.0 ✓ | — | — | src |
| Radeon AI Pro R9700 · 32 GB | LFM2.5-350M | MQ4 | hipfire 0.3.0+439233d92959 | 4096 | 466.0 ✓ | — | — | src |
| Radeon AI Pro R9700 · 32 GB | Qwen3.5-27B | MQ4-AWQ | hipfire 0.2.0+3730b58 | 4096 | 286.6 ✓ | 435.7 | 17.5 | src |
| Radeon AI Pro R9700 · 32 GB | LFM2.5-8B-A1B | MQ4 | hipfire 0.2.0+d38a269d | 4096 | 241.1 ✓ | 242.1 | 5.4 | src |
| Radeon AI Pro R9700 · 32 GB | gemma-4-E2B-it | Q8_0 | llama.cpp b9333-35c9b1f39 | 2048 | 169.7 ✓ | 9649.1 | — | src |
| Radeon AI Pro R9700 · 32 GB | gemma-4-E4B-it | Q4_K_M | llama.cpp b9333-35c9b1f39 | 2048 | 137.0 ✓ | 4441.8 | — | src |
| Radeon AI Pro R9700 · 32 GB | Muse-Glimmer-30B | Dynamic-Q4_K_XL + DFlash2-Q4_K_M | llama.cpp 0.3.0-dev / build 10680 / commit d7b… | 32768 | 134.6 ✓ | 380.6 | 23.6 | src |
| Radeon AI Pro R9700 · 32 GB | Qwen3.8-27B | Q4_0 | llama.cpp b10711 | 262144 | 64.3 ✓ | — | — | src |
| Radeon AI Pro R9700 · 32 GB | DeepSeek-V4-Flash-0731 | IQ2_XXS | lucebox c994209 | 8192 | 59.4 ✓ | 196.1 | 25.2 | src |
| Radeon AI Pro R9700 · 32 GB | Qwen 3.8 Flash-Next Base | IQ3_S | xestrata xe0.1.42 | 128000 | 57.0 ✓ | 119.4 | — | src |
| Radeon AI Pro R9700 · 32 GB | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp 035e227 + Qwen4Exp graph-reuse/QSA t… | 32768 | 25.6 ✓ | 537.4 | 32.9 | src |
| Radeon AI Pro R9700 · 32 GB | GLM-5.3-Flash | UD-IQ1_M | llama.cpp 2e0e57f10 | 32768 | 17.4 ✓ | 39.6 | 92.2 | src |
| Radeon AI Pro R9700 · 32 GB | Ling-3.0-tiny | Q4_K_M | llama.cpp — | 2048 | 113.4 … | 7088.9 | — | src |
| Radeon AI Pro R9700 · 32 GB | GLM-4.7-Flash | Q2_K_XL | llama.cpp — | 2048 | 82.0 … | 2046.4 | — | src |
| Radeon AI Pro R9700 · 32 GB | Qwen3.6-35B-A3B | Q4_K_XL | llama.cpp — | 2048 | 78.6 … | 2883.3 | — | src |
| Radeon AI Pro R9700 · 32 GB | gemma-4-12B-it | Q4_K_M | llama.cpp — | 2048 | 58.2 … | 2350.8 | — | src |
| Radeon AI Pro R9700 · 32 GB | Qwen3.5-27B | Q4_K_XL | llama.cpp — | 2048 | 26.7 … | 1099.5 | — | src |
| Radeon AI Pro R9700 · 32 GB | gemma-4-31B-it | Q4_K_XL | llama.cpp — | 2048 | 25.4 … | 923.1 | — | src |