Can I run Qwen3.6 27B on an RTX 3090?
Yes: Qwen3.6 27B needs about 19.9 GB at Q4_K_M with 32K tokens of context, which fits the 24 GB RTX 3090 with 4.08 GB to spare. At 32K the RTX 3090 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
- RTX 3090
- 24 GB, 936 GB/s
- To spare
- 4.08 GB
- Tokens/s
- 26–36 tokens/s
At Q4_K_M with 32K tokens of context it writes about 26–36 tokens/s for one request on an RTX 3090.
Best precision for Qwen3.6 27B on an RTX 3090
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 | 25–34 |
| 32K | Q5_K_M | 22.9 GB | 1.13 GB | 23–32 |
| 128K | Q3_K_M | 23.2 GB | 809 MB | 22–31 |
| 256K (full) | Nothing fits | — | — | — |
Qwen3.6 27B on the RTX 3090 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 | 29–40 | 31.0 GB | −7.01 GB | — |
| 8K | 18.3 GB | 5.73 GB | 28–40 | 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 | 26–36 | 32.9 GB | −8.94 GB | — |
| 64K | 22.1 GB | 1.88 GB | 24–33 | 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 | — |
Qwen3.6 27B on more than one RTX 3090
| Cards | Best at 32K | Tokens/s | Q4_K_M longest | Q4_K_M tokens/s | Rent per hour |
|---|---|---|---|---|---|
| 2× (48 GB) | Q8_0 | 29–42 | 256K (full) | 46–68 | $0.54 |
| 4× (96 GB) | BF16 | 32–46 | 256K (full) | 79–124 | $1.08 |
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 RTX 3090; it fits with 0.5 GB to spare up to 131K tokens.
- Renting an RTX 3090 costs about $0.27 an hour (median on getdeploying.com, 2026-09-29): $2.1–2.9 per million tokens at 26–36 tokens/s.
- Smallest setup for Q4_K_M at 32K: RTX 3090 (24 GB).
Run Qwen3.6 27B on the RTX 3090 with llama-server
llama-server -hf ggml-org/Qwen3.6-27B-GGUF:Q4_K_M -c 50176Qwen3.6-27B-Q4_K_M.gguf, 19.1 GB, from ggml-org/
Questions
Can I run Qwen3.6 27B on an RTX 3090?
Yes: Qwen3.6 27B needs about 19.9 GB at Q4_K_M with 32K tokens of context, which fits the 24 GB RTX 3090 with 4.08 GB to spare. At 32K the RTX 3090 holds up to Q5_K_M (22.9 GB), and Q4_K_M runs up to 83K tokens.
How fast is Qwen3.6 27B on an RTX 3090?
At Q4_K_M with 32K tokens of context it writes about 26–36 tokens/s for one request on an RTX 3090.
What does a second RTX 3090 change for Qwen3.6 27B?
Two RTX 3090 cards (48 GB in one tensor-parallel group) hold Qwen3.6 27B at Q8_0 with 32K, and Q4_K_M up to 256K (full) tokens, at about 46–68 tokens/s.
Try other settings in the VRAM calculator or the speed calculator. See also Qwen3.6 27B VRAM requirements, what LLMs an RTX 3090 can run and every pair, or detect your own GPU. Model data checked .