Fastest
Qwen3.8-27B-UD-IQ4_XS
27B
75.0 tok/s
Highest token generation speed at 75.0 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RTX 2060
Compare RTX 2060 benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 6GB
Recommended Models
Models we recommend for RTX 2060.
Best quality
IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF:1
35B
25.9 tok/sQuality 87.5
Highest completed quality score at 87.5.
Largest context
peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q6_K_XL
2B
61.3 tok/sContext 65,536 tokens
Largest context that fits in 6GB VRAM, at 65,536 tokens.
Frequently asked questions
Which models actually run best on the RTX 2060, by task, from community benchmark data.
- What is the best local model for coding on the RTX 2060?
- On the RTX 2060, IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF:1 ranks first for coding in our benchmarks (84.9/100 at ~25.2 tok/s). Qwen3.8-27B-UD-IQ4_XS is faster (~70.6 tok/s) and still scores well (82.3/100) — 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 2060?
- On the RTX 2060, openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_K_M ranks first for agentic workflows in our benchmarks (89.1/100 at ~19.0 tok/s). Qwen3.8-27B-UD-IQ4_XS is faster (~70.6 tok/s) and still scores well (88.9/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA GeForce RTX 2060.