Can I run Qwen3.8-27B on an RTX 4060?
Yes, with a GGUF version
The published weights are too big, but the mtp-Qwen3.8-27B-BF16 file from ggml-org/Qwen3.8-27B-GGUF (5.95 GB) fits, with room for ≈ 16K tokens of context.
Full analysis of Qwen3.8-27B
Everything that runs on RTX 4060
Get the mtp-Qwen3.8-27B-BF16 file on Hugging Face
ollama run hf.co/ggml-org/Qwen3.8-27B-GGUFFiles and context on RTX 4060
Each file of Qwen3.8-27B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On RTX 4060 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 55.6 GB | Doesn't fit | — | — |
| BF16 | 53.8 GB | Doesn't fit | — | — |
| Q8_0 | 28.6 GB | Doesn't fit | — | — |
| Q4_K_M | 19.0 GB | Doesn't fit | — | — |
| mtp-Qwen3.8-27B-BF16 | 5.95 GB | Tight | 16K | 33K |
| IQ4_XS | 13.1 GB | Doesn't fit | — | — |
| IQ3_S | 11.0 GB | Doesn't fit | — | — |
| IQ3_XS | 10.4 GB | Doesn't fit | — | — |
| IQ3_XXS | 9.92 GB | Doesn't fit | — | — |
| IQ2_XXS | 8.84 GB | Doesn't fit | — | — |
Qwen3.8-27B on other hardware
- NVIDIA H100Yes
- RTX 5090Yes, with a GGUF version
- RTX 4090Yes, with a GGUF version
- RTX 3090Yes, with a GGUF version
- RTX 5060 Ti 16 GBYes, with a GGUF version
- RTX 3060 12 GBYes, with a GGUF version
- RTX 4060Yes, with a GGUF version
- Mac with 32 GBYes, with a GGUF version
- Mac with 64 GBYes, with a GGUF version
- Mac with 128 GBYes