Fastest
ProCreations_grug-35b-v2-Q5_K_L
35B
65.2 tok/s
Highest token generation speed at 65.2 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RTX 3060 + RTX 3060 + RTX 4070
Compare RTX 3060 + RTX 3060 + RTX 4070 benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 36GB
- Architecture
- Multi-GPU
Recommended Models
Models we recommend for RTX 3060 + RTX 3060 + RTX 4070.
Best quality
mudler-Ornith-1.5-35B-A3B-APEX-I-Quality-GGUF
35B
59.5 tok/sQuality 85.1
Highest completed quality score at 85.1.
Frequently asked questions
Which models actually run best on the RTX 3060 + RTX 3060 + RTX 4070, by task, from community benchmark data.
- What is the best local model for coding on the RTX 3060 + RTX 3060 + RTX 4070?
- On the RTX 3060 + RTX 3060 + RTX 4070, mudler-Ornith-1.5-35B-A3B-APEX-I-Quality-GGUF ranks first for coding in our benchmarks (80.2/100 at ~59.5 tok/s).
- What is the best local model for agentic workflows on the RTX 3060 + RTX 3060 + RTX 4070?
- On the RTX 3060 + RTX 3060 + RTX 4070, mudler-Ornith-1.5-35B-A3B-APEX-I-Quality-GGUF ranks first for agentic workflows in our benchmarks (88.8/100 at ~59.5 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA GeForce RTX 3060 + NVIDIA GeForce RTX 3060 + NVIDIA GeForce RTX 4070.