Fastest
qwen3.8-9b-distill
9B
119.5 tok/s
Highest token generation speed at 119.5 tok/s.
Hardware Benchmarks
Best Local LLM Performance for 2× A10g
Compare 2× A10g benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 48GB
- Architecture
- Multi-GPU
Recommended Models
Models we recommend for 2× A10g.
Best quality
qwen3.8-27b
27B
79.4 tok/sQuality 85.0
Highest completed quality score at 85.0.
Frequently asked questions
Which models actually run best on the 2× A10g, by task, from community benchmark data.
- What is the best local model for coding on the 2× A10g?
- On the 2× A10g, qwen3.8-27b ranks first for coding in our benchmarks (80.2/100 at ~79.4 tok/s).
- What is the best local model for agentic workflows on the 2× A10g?
- On the 2× A10g, qwen3.8-27b ranks first for agentic workflows in our benchmarks (87.3/100 at ~79.4 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for 2× NVIDIA A10G.