LLM Quantization Benchmark on Apple Silicon

What is LLM Quantization Benchmark on Apple Silicon?

Benchmark measuring inference speed, memory usage, and accuracy of MLX and llama.cpp with 4-bit and 8-bit quantization across three 3B-class LLMs on Apple M4…

Released

2026-09-13

Evaluates

Language & Knowledge, Software & AI Compute, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://github.com/sameer-sde/llm-quantization-benchmark

LLM Quantization Benchmark on Apple Silicon code

• Code https://github.com/sameer-sde/llm-quantization-benchmark

Which sources cite LLM Quantization Benchmark on Apple Silicon?

• LLM Quantization Benchmark on Apple Silicon

Related Language & Knowledge, Software & AI Compute, cs.AI benchmarks

• 2d-fet-bench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABACUS
• ABC-Bench
• Active-SWE
• ActiveSciBench