Community performance summary

DeepSeek Coder V2 Lite Instruct

1 GPU configurations measured with this model. Compare hardware differences, quantizations and every recorded result.

3 signed runs · 0 verified · 1 tester
Median prompt111.55tok/s · 92.48 to 111.72
Median generation13.52tok/s · 7.56 to 16.37
Configurations1IQ2_XS
Last observedSep 25GCN / Vega

What the results show

One clear view.
Every recorded run.

Measurements from comparable hardware and models are presented together. Medians show typical performance, while every signed run remains available below for inspection and sharing.

Hardware tested1 groups
AMD Radeon Pro 560X3 runs→
macOS

macOS 15.8 Sequoia

Recorded evidence

Inspect every run.

Open any result to review its exact hardware, model configuration, measurements and submission details.

1 to 8 of 3 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
DeepSeek Coder V2 Lite InstructIQ2_XS · MoE · Signed ToshLLM app · ncmoe 16 · amd-gpu · Metal · comparison
GCN / Vega
111.72tok/s
16.37tok/s
mitchdeSep 24, 2026
DeepSeek Coder V2 Lite InstructIQ2_XS · MoE · Signed ToshLLM app · ncmoe 16 · amd-gpu · Metal · comparison
GCN / Vega
111.55tok/s
13.52tok/s
mitchdeSep 25, 2026
DeepSeek Coder V2 Lite InstructIQ2_XS · MoE · Signed ToshLLM app · ncmoe 50 · amd-gpu · Metal · comparison
GCN / Vega
92.48tok/s
7.56tok/s
mitchdeSep 18, 2026