First-party launch recipes
Recipes
One model on one card, with ROCm metadata and a sourced proof. llama.cpp is the consumer default. Decode cells stay empty until a sourced run exists. Q3 is labeled estimate or community unless we measured it. Q1/Q2 stay off.
7 live recipes · catalog also at /recipes.json.
How we test — Measured cells cite official amdai-bench/run@1 cards. Estimates stay labeled. Q3 is estimate-only. Q1/Q2 stay off.
Models GPU directory Calculator Stack Lab
r9700 · gfx1201
AMD Radeon AI PRO R9700
| Model | Setup | Backend | Quant | Ctx | Decode | Evidence |
|---|---|---|---|---|---|---|
| Qwen3.6-35B-A3B Qwen3.6-35B-A3B-Q4_K_M.gguf | 1× r9700 | llama.cpp vulkan | Q4_K_M | short | 117.69 | Tested on our rig |
| Qwen3.6-35B-A3B Qwen3.6-35B-A3B-Q5_K_M.gguf | 1× r9700 | llama.cpp vulkan | Q5_K_M | short | 109.73 | Tested on our rig |
| Qwen3.6-35B-A3B Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf | 1× r9700 | llama.cpp vulkan | UD-Q5_K_XL | 256K | 44.4 | Tested on our rig |
| Qwen3.6-35B-A3B Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf | 1× r9700 | llama.cpp vulkan | UD-Q5_K_XL | 32K | 90.52 | Tested on our rig |
| Qwen3.6-35B-A3B Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf | 1× r9700 | llama.cpp vulkan | UD-Q5_K_XL | short | 102.39 | Tested on our rig |
| Qwen 3.8 Flash UD-Q6_K_XL (folder) | 2× r9700 | llama.cpp vulkan | UD-Q6_K_XL | 262K | 16 | Tested on our rig |
| Qwen 3.8 Flash UD-Q6_K_XL (folder) | 2× r9700 | Strata hip | UD-Q6_K_XL | 262K | 32.6 | Tested on our rig |