Leaderboard/DeepSeek-Coder-V2-Lite-Instruct-4bit/M3 Ultra (60-core GPU)/r_l_v1-zq_qaz

DeepSeek-Coder-V2-Lite-Instruct-4bit on M3 Ultra (60-core GPU) + 96GB unified

Name: DeepSeek-Coder-V2-Lite-Instruct-4bit on M3 Ultra (60-core GPU) + 96GB unified
Creator: llm-speed
License: https://www.apache.org/licenses/LICENSE-2.0
Keywords: LLM benchmark, tokens per second, DeepSeek-Coder-V2-Lite-Instruct-4bit, M3 Ultra (60-core GPU) + 96GB unified, mlx

M3 Ultra (60-core GPU) + 96GB unified

suite suite-v1

cli 0.0.1-dev

signedG8xb3zMu3+…

submitted Apr 28, 2026

https://llm-speed.com/r/r_l_v1-zq_qaz

Workload results

Workload	Backend	Model	decode tok/s	prefill tok/s	TTFT	p50	p95
chat-short	mlx@0.31.3	mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit	168.3tok/s	291.5tok/s	449ms	5.9ms	6.1ms

Embed this run

Drop the badge into a README, blog post, or signature. Each render is a backlink to the signed result.

[![llm-speed: 168 tok/s on M3 Ultra (60-core GPU) (DeepSeek-Coder-V2-Lite-Instruct…)](https://llm-speed.com/badge/r_l_v1-zq_qaz.svg)](https://llm-speed.com/r/r_l_v1-zq_qaz)

Related benchmarks

More DeepSeek-Coder-V2-Lite-Instruct-4bit benchmarks — every backend and rig that has run this model.
More M3 Ultra (60-core GPU) LLM benchmarks — every model measured on this hardware.

Provenance

Run ID: r_l_v1-zq_qaz
Fingerprint hash: bbf15132ccbbe7d7
Public key: G8xb3zMu3+pznEici/TiW0gPk5qSNIYIikGCwm1rMdQ=
Received: 2026-04-28 14:31:36