Leaderboard/llama-3.3-70b-Instruct-4bit/M3 Ultra (60-core GPU)/r_sx3a4y9n-m4

llama-3.3-70b-Instruct-4bit on M3 Ultra (60-core GPU) + 96GB unified

Name: llama-3.3-70b-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, llama-3.3-70b-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_sx3a4y9n-m4

Workload results

Workload	Backend	Model	decode tok/s	prefill tok/s	TTFT	p50	p95
chat-short	mlx@0.31.3	mlx-community/llama-3.3-70b-Instruct-4bit	16.78tok/s	25.09tok/s	5,420ms	59.6ms	59.8ms

Embed this run

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

[![llm-speed: 16.8 tok/s on M3 Ultra (60-core GPU) (llama-3.3-70b-Instruct-4bit)](https://llm-speed.com/badge/r_sx3a4y9n-m4.svg)](https://llm-speed.com/r/r_sx3a4y9n-m4)

Related benchmarks

More llama-3.3-70b-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_sx3a4y9n-m4
Fingerprint hash: bbf15132ccbbe7d7
Public key: G8xb3zMu3+pznEici/TiW0gPk5qSNIYIikGCwm1rMdQ=
Received: 2026-04-28 14:45:36