Fastest
DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF
2.6B
176.0 tok/s
Highest token generation speed at 176.0 tok/s.
Hardware Benchmarks
Best Local LLM Performance for 2× RTX 3080
Compare 2× RTX 3080 benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 40GB
- Architecture
- Multi-GPU
Recommended Models
Models we recommend for 2× RTX 3080.
Best quality & Largest context tested
qwen3.8-flash-next-unsloth-ud-iq4_xs
Unknown
81.1 tok/sQuality 84.7Context 262,144 tokens
Highest completed quality score at 84.7. Largest context window tested on this hardware, at 262,144 tokens.
Models on the 2× RTX 3080
Every model the community ran on this hardware. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Best trade-off: quality 60+, and nothing else here is both faster and betterOther models · dot size = number of runs
Medians over 10 fully rated runs of 6 models. Each quantization is its own model.
Frequently asked questions
Which models actually run best on the 2× RTX 3080, by task, from community benchmark data.
- What is the best local model for coding on the 2× RTX 3080?
- On the 2× RTX 3080, qwen3.8-flash-next-unsloth-ud-q4_k_xl ranks first for coding in our benchmarks (77.8/100 at ~66.7 tok/s).
- What is the best local model for agentic workflows on the 2× RTX 3080?
- On the 2× RTX 3080, qwen3.8-flash-next-unsloth-ud-q4_k_xl ranks first for agentic workflows in our benchmarks (86.3/100 at ~66.7 tok/s). qwen3.8-flash-next-iq3_s is faster (~117.4 tok/s) and still scores well (83.7/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for 2× NVIDIA GeForce RTX 3080.