community pool / model answer

DeepSeek-Coder-V2-Lite-Instruct-GGUF

code · bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF

57.1 tok/s · model median · 1 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
Arc Pro B70 32GB	4-bit	57.1 tok/s	reported	140	- GB	2,048	llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.