Can I run Qwen3.8 27B on an RX 7900 XTX?
Yes: Qwen3.8 27B needs about 19.9 GB at Q4_K_M with 32K tokens of context, which fits the 24 GB RX 7900 XTX with 4.08 GB to spare. At 32K the RX 7900 XTX holds up to Q5_K_M (22.9 GB), and Q4_K_M runs up to 83K tokens.
Yes Q4_K_M with 32K tokens of context
- Q4_K_M, 32K
- 19.9 GB
- RX 7900 XTX
- 24 GB, 960 GB/s
- To spare
- 4.08 GB
- Tokens/s
- 27–37 tokens/s
At Q4_K_M with 32K tokens of context it writes about 27–37 tokens/s for one request on an RX 7900 XTX.
Best precision for Qwen3.8 27B on an RX 7900 XTX
The most precise setting that leaves at least 0.5 GB free; one that fits with less is marked tight.
| Context | Best fit | Memory | Free | Tokens/s |
|---|---|---|---|---|
| 8K | Q5_K_M | 21.2 GB | 2.78 GB | 25–35 |
| 32K | Q5_K_M | 22.9 GB | 1.13 GB | 23–32 |
| 128K | Q3_K_M | 23.2 GB | 809 MB | 23–32 |
| 256K (full) | Nothing fits | — | — | — |
Qwen3.8 27B on the RX 7900 XTX as the context fills
One request, FP16 KV cache, 0.5 GB plus 10% overhead; a minus sign is memory missing, and tight is less than 0.5 GB free.
| Context | Q4_K_M | Free | Tokens/s | Q8_0 | Free | Tokens/s |
|---|---|---|---|---|---|---|
| 4K | 18.0 GB | 6.01 GB | 30–41 | 31.0 GB | −7.01 GB | — |
| 8K | 18.3 GB | 5.73 GB | 29–41 | 31.3 GB | −7.29 GB | — |
| 16K | 18.8 GB | 5.18 GB | 28–39 | 31.8 GB | −7.84 GB | — |
| 32K | 19.9 GB | 4.08 GB | 27–37 | 32.9 GB | −8.94 GB | — |
| 64K | 22.1 GB | 1.88 GB | 24–34 | 35.1 GB | −11.1 GB | — |
| 128K | 26.5 GB | −2.52 GB | — | 39.5 GB | −15.5 GB | — |
| 256K (full) | 35.3 GB | −11.3 GB | — | 48.3 GB | −24.3 GB | — |
Qwen3.8 27B on more than one RX 7900 XTX
| Cards | Best at 32K | Tokens/s | Q4_K_M longest | Q4_K_M tokens/s |
|---|---|---|---|---|
| 2× (48 GB) | Q8_0 | 30–43 | 256K (full) | 47–69 |
| 4× (96 GB) | BF16 | 32–47 | 256K (full) | 80–127 |
Tensor parallel with the combined bandwidth, as in vLLM; llama.cpp splits layers by default and runs at about one card's speed.
Other options
- The next smaller setting, Q3_K_M, takes 16.6 GB at 32K, 7.39 GB under the RX 7900 XTX; it fits with 0.5 GB to spare up to 131K tokens.
- Smallest setup for Q4_K_M at 32K: RTX 3090 (24 GB).
Run Qwen3.8 27B on the RX 7900 XTX with llama-server
llama-server -hf ggml-org/Qwen3.8-27B-GGUF:Q4_K_M -c 52224Qwen3.8-27B-Q4_K_M.gguf, 19.0 GB, from ggml-org/
Questions
Can I run Qwen3.8 27B on an RX 7900 XTX?
Yes: Qwen3.8 27B needs about 19.9 GB at Q4_K_M with 32K tokens of context, which fits the 24 GB RX 7900 XTX with 4.08 GB to spare. At 32K the RX 7900 XTX holds up to Q5_K_M (22.9 GB), and Q4_K_M runs up to 83K tokens.
How fast is Qwen3.8 27B on an RX 7900 XTX?
At Q4_K_M with 32K tokens of context it writes about 27–37 tokens/s for one request on an RX 7900 XTX.
What does a second RX 7900 XTX change for Qwen3.8 27B?
Two RX 7900 XTX cards (48 GB in one tensor-parallel group) hold Qwen3.8 27B at Q8_0 with 32K, and Q4_K_M up to 256K (full) tokens, at about 47–69 tokens/s.
Try other settings in the VRAM calculator or the speed calculator. See also Qwen3.8 27B VRAM requirements, what LLMs an RX 7900 XTX can run and every pair, or detect your own GPU. Model data checked .