What is the best local model for coding on the 2× Tesla T4?

On the 2× Tesla T4, Ternary-Bonsai-2-27B-PTQ1_0 ranks first for coding in our benchmarks (84.5/100 at ~30.5 tok/s).

What is the best local model for agentic workflows on the 2× Tesla T4?

On the 2× Tesla T4, Ternary-Bonsai-2-27B-PTQ1_0 ranks first for agentic workflows in our benchmarks (89.7/100 at ~30.5 tok/s).

Hardware Benchmarks

Compare 2× Tesla T4 benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

2× Tesla T4

Models we recommend for 2× Tesla T4.

Fastest

80.1 tok/s

Highest token generation speed at 80.1 tok/s.

Best quality & Largest context

27B

30.5 tok/sQuality 87.3Context 32,768 tokens

Highest completed quality score at 87.3. Largest context that fits in 30GB VRAM, at 32,768 tokens.

Which models actually run best on the 2× Tesla T4, by task, from community benchmark data.

What is the best local model for coding on the 2× Tesla T4?: On the 2× Tesla T4, Ternary-Bonsai-2-27B-PTQ1_0 ranks first for coding in our benchmarks (84.5/100 at ~30.5 tok/s).
What is the best local model for agentic workflows on the 2× Tesla T4?: On the 2× Tesla T4, Ternary-Bonsai-2-27B-PTQ1_0 ranks first for agentic workflows in our benchmarks (89.7/100 at ~30.5 tok/s).

Completed quality-ranked benchmark results for 2× Tesla T4.