What is the best local model for coding on the Gtx 1070?

On the Gtx 1070, llama3:latest ranks first for coding in our benchmarks (23.6/100 at ~32.4 tok/s).

What is the best local model for agentic workflows on the Gtx 1070?

On the Gtx 1070, gemma3:latest ranks first for agentic workflows in our benchmarks (74.0/100 at ~35.5 tok/s).

Hardware Benchmarks

Compare Gtx 1070 benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce GTX 1070

Models we recommend for Gtx 1070.

Fastest & Best quality & Largest context

3.9B

35.5 tok/sQuality 49.2Context 8,192 tokens

Highest token generation speed at 35.5 tok/s. Highest completed quality score at 49.2. Largest context that fits in 8GB VRAM, at 8,192 tokens.

Which models actually run best on the Gtx 1070, by task, from community benchmark data.

What is the best local model for coding on the Gtx 1070?: On the Gtx 1070, llama3:latest ranks first for coding in our benchmarks (23.6/100 at ~32.4 tok/s).
What is the best local model for agentic workflows on the Gtx 1070?: On the Gtx 1070, gemma3:latest ranks first for agentic workflows in our benchmarks (74.0/100 at ~35.5 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce GTX 1070.