Fastest
QwenPaw-Flash-4B-Q4_K_M
4B
123.2 tok/s
Highest token generation speed at 123.2 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RTX A6000
Compare RTX A6000 benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 47GB
Recommended Models
Models we recommend for RTX A6000.
Best quality & Largest context
NeoHorse-1-4B-GGUF
4B
102.8 tok/sQuality 69.3Context 262,144 tokens
Highest completed quality score at 69.3. Largest context that fits in 47GB VRAM, at 262,144 tokens.
Frequently asked questions
Which models actually run best on the RTX A6000, by task, from community benchmark data.
- What is the best local model for coding on the RTX A6000?
- On the RTX A6000, NeoHorse-1-4B-GGUF ranks first for coding in our benchmarks (56.0/100 at ~102.8 tok/s).
- What is the best local model for agentic workflows on the RTX A6000?
- On the RTX A6000, NeoHorse-1-4B-GGUF ranks first for agentic workflows in our benchmarks (72.4/100 at ~102.8 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA RTX A6000.