Fastest & Best quality
Qwen3.8-27B-Q8-DFlash2
27B
69.9 tok/sQuality 86.6
Highest token generation speed at 69.9 tok/s. Highest completed quality score at 86.6.
Hardware Benchmarks
Best Local LLM Performance for RTX 5090 Laptop
Compare RTX 5090 Laptop benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 23GB
Recommended Models
Models we recommend for RTX 5090 Laptop.
Frequently asked questions
Which models actually run best on the RTX 5090 Laptop, by task, from community benchmark data.
- What is the best local model for coding on the RTX 5090 Laptop?
- On the RTX 5090 Laptop, Qwen3.8-27B-Q4-MTP ranks first for coding in our benchmarks (83.5/100 at ~48.2 tok/s). Qwen3.8-27B-Q8-DFlash2 is faster (~69.9 tok/s) and still scores well (82.4/100) — a good pick if you'd rather trade a little quality for speed.
- What is the best local model for agentic workflows on the RTX 5090 Laptop?
- On the RTX 5090 Laptop, Qwen3.8-27B-Q4-MTP ranks first for agentic workflows in our benchmarks (87.7/100 at ~48.2 tok/s). Qwen3.8-27B-Q8-DFlash2 is faster (~69.9 tok/s) and still scores well (84.2/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA GeForce RTX 5090 Laptop GPU.