Can Qwen3.8 27B run on the RTX 3090 Ti?
Yes. At 8K context the best fit is Q4_K_M, using about 17.6 GB of the 22.8 GB usable on the RTX 3090 Ti. Estimated speed ceiling: ~58 tokens/sec.
+ 0.9 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q4_K_M at 8K context then needs about 18.5 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 11.2 GB Fits | 11.5 GB Fits | 13.0 GB Fits | 19.0 GB Fits | 93 |
| 3-bit (Q3_K_M) • | 13.6 GB Fits | 13.9 GB Fits | 15.4 GB Fits | 21.4 GB Tight | 75 |
| 4-bit (Q4_K_M) • | 17.4 GB Fits | 17.6 GB Fits | 19.1 GB Fits | 25.1 GB No | 58 |
| 5-bit (Q5_K_M) • | 20.6 GB Tight | 20.9 GB Tight | 22.4 GB Tight | 28.4 GB No | 48 |
| 6-bit (Q6_K) • | 23.3 GB No | 23.6 GB No | 25.1 GB No | 31.1 GB No | — |
| 8-bit (Q8_0) • | 28.2 GB No | 28.5 GB No | 30.0 GB No | 36.0 GB No | — |
| 16-bit (F16/BF16) • | 52.0 GB No | 52.3 GB No | 53.8 GB No | 59.8 GB No | — |
• real GGUF file size from bartowski/Qwen3.8-27B-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Qwen3.8 27B: RX 7900 XTX (24 GB, launch MSRP $999) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3090 Ti: GLM 4.7 Flash (31B, MoE) at Q4_K_M, about 18.3 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Qwen3.8 27B on every GPU and Mac · Every model that runs on the RTX 3090 Ti · Other models that fit 24 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (Qwen/Qwen3.8-27B), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.