Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP
| GPU(s) | AMD Radeon RX 7900 XTX Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 24 |
| CPU | AMD Ryzen 5 3600 Amazon · eBay (used) · Newegg |
| Motherboard | |
| RAM | 128 GiB Amazon · eBay (used) · Newegg |
| PSU | |
| Other | llama.cpp ROCm build be4a6a6 |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| Qwen3.6 35B-A3B | UD-Q4_K_XL, llama-bench 2K, f16 KV | llama.cpp ROCm | 87.2 | |
| Qwen3.6 35B-A3B | UD-Q4_K_XL, ~16K real-text context, q4_0 KV | llama.cpp ROCm (llama-server) | 79.6 | |
| Qwen3.6 35B-A3B | UD-Q4_K_XL + MTP (draft-n-max 4), ~16K context | llama.cpp ROCm (llama-server) | 135.2 | ⚡ spec-decode (MTP) |
| Qwen3.6 35B-A3B | UD-Q4_K_XL, ~64K context | llama.cpp ROCm (llama-server) | 66.0 | |
| Qwen3.6 35B-A3B | UD-Q4_K_XL + MTP, ~64K context | llama.cpp ROCm (llama-server) | 108.2 | ⚡ spec-decode (MTP) |
| Qwen3.6 35B-A3B | UD-Q4_K_XL, ~245K context, q4_0 KV | llama.cpp ROCm (llama-server) | 38.3 |
GitHub gist created 26 Jun 2026. All layers on the GPU (21.27 GiB model). Only q4_0 KV fits the full 256K context; MTP fits up to about 200K. The same gist measured the dense 27B at 29 tok/s plain and 50 with MTP at 16K.
Source: https://gist.github.com/AshyIsMe/ef9dc0e57d7af5626f3935f55c38543a
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)
Quick answers: Can Radeon RX 7900 XTX run Qwen3.6 35B-A3B?