Fits comfortably
Running Qwen 2.5 Coder 14B Instruct on NVIDIA GeForce RTX 5080
NVIDIA GeForce RTX 5080 runs Qwen 2.5 Coder 14B Instruct comfortably at Q4_K_M with 5 GB of headroom for context.
Model size
14B params
Qwen 2.5 Coder 14B Instruct →Memory available
Recommended quant
Q4_K_M
Highest quality that fits
Variants and what fits
| Quantization | File size | VRAM required | Fits on NVIDIA GeForce RTX 5080? |
|---|---|---|---|
| Q4_K_M | 8.4 GB | 11 GB | Yes |
Real benchmarks
Frequently asked
Can NVIDIA GeForce RTX 5080 run Qwen 2.5 Coder 14B Instruct?
NVIDIA GeForce RTX 5080 runs Qwen 2.5 Coder 14B Instruct comfortably at Q4_K_M with 5 GB of headroom for context.
What quantization should I use?
Q4_K_M is the highest-quality variant of Qwen 2.5 Coder 14B Instruct that fits in 16 GB VRAM. Lower-bit quants will be smaller but lose some quality.
How fast will it be?
Measured at 79.0 tok/s on this combination in our testing.
See also: Qwen 2.5 Coder 14B Instruct, NVIDIA GeForce RTX 5080, all benchmarks.
Reviewed by RunLocalAI Editorial. See our editorial policy.