Radeon RX 7900 XTX for local LLMs
6 measured results from 1 builds, each linked to its source.
| Memory | 24 GB per card |
|---|---|
| Memory bandwidth | not listed |
| Typical EU price | not tracked yet |
Can it run? Qwen3.6 35B-A3B on Radeon RX 7900 XTX
All builds with the Radeon RX 7900 XTX
| Build | GPU(s) | Memory GB (total) | Results |
|---|---|---|---|
| Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | AMD Radeon RX 7900 XTX | 24 | 6 |
All measured results
(MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)
| Model | Build | Ran on | Quant | Engine | tok/s | Details |
|---|---|---|---|---|---|---|
| Qwen3.6 35B-A3B | Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | Radeon RX 7900 XTX | 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 | Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | Radeon RX 7900 XTX | UD-Q4_K_XL + MTP, ~64K context | llama.cpp ROCm (llama-server) | 108.2 | ⚡ spec-decode (MTP) |
| Qwen3.6 35B-A3B | Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | Radeon RX 7900 XTX | UD-Q4_K_XL, llama-bench 2K, f16 KV | llama.cpp ROCm | 87.2 | |
| Qwen3.6 35B-A3B | Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | Radeon RX 7900 XTX | UD-Q4_K_XL, ~16K real-text context, q4_0 KV | llama.cpp ROCm (llama-server) | 79.6 | |
| Qwen3.6 35B-A3B | Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | Radeon RX 7900 XTX | UD-Q4_K_XL, ~64K context | llama.cpp ROCm (llama-server) | 66.0 | |
| Qwen3.6 35B-A3B | Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP | Radeon RX 7900 XTX | UD-Q4_K_XL, ~245K context, q4_0 KV | llama.cpp ROCm (llama-server) | 38.3 |
All Radeon RX 7900 XTX builds: see also all GPUs · best LLMs by memory size · download the dataset.
FAQ
How fast is the Radeon RX 7900 XTX for local LLMs?
The fastest plain-decode result we have is 87.2 tok/s on Qwen3.6 35B-A3B (UD-Q4_K_XL, llama-bench 2K, f16 KV, llama.cpp ROCm) in Radeon RX 7900 XTX (24 GB): Qwen3.6 35B-A3B up to 245K context, with MTP. Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 6 measured results from 1 builds.
How much memory does the Radeon RX 7900 XTX have?
24 GB per card.
Which models have been measured on the Radeon RX 7900 XTX?
Qwen3.6 35B-A3B.
Where do these numbers come from?
Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.