Fastest
mistralai/ministral-3-3b
3B
77.5 tok/s
Highest token generation speed at 77.5 tok/s.
Hardware Benchmarks
Best Local LLM Performance for 4× Gtx 1080 Ti
Compare 4× Gtx 1080 Ti benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 44GB
- Architecture
- Multi-GPU
Recommended Models
Models we recommend for 4× Gtx 1080 Ti.
Best quality
qwen/qwen3.8-27b
27B
16.1 tok/sQuality 75.3
Highest completed quality score at 75.3.
Largest context
qwen/qwen3.5-9b
9B
34.6 tok/sContext 2,048,000 tokens
Largest context that fits in 44GB VRAM, at 2,048,000 tokens.
Frequently asked questions
Which models actually run best on the 4× Gtx 1080 Ti, by task, from community benchmark data.
- What is the best local model for coding on the 4× Gtx 1080 Ti?
- On the 4× Gtx 1080 Ti, google/gemma-4-12b-qat ranks first for coding in our benchmarks (72.8/100 at ~27.8 tok/s).
- What is the best local model for agentic workflows on the 4× Gtx 1080 Ti?
- On the 4× Gtx 1080 Ti, qwen/qwen3.8-27b ranks first for agentic workflows in our benchmarks (85.7/100 at ~16.1 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for 4× NVIDIA GeForce GTX 1080 Ti.