verifiedmedium · 0.80updated 2026-10-15

LLMCheck: Apple M5 Max (64GB), Ollama, Qwen3.6-35B-A3B Q4_K_M decode

48.0 tok/s (decode, per-request)

Fields

benchmarks/llmcheck-m5-max-qwen36-35b-a3b-ollama-decode

Metric

decode_tok_s

Value

Unit

tok/s (decode, per-request)

Model

Qwen3.6-35B-A3B

Methodology

THIRD-PARTY MEASURED (LLMCheck open dataset). M5 Max 64GB, Ollama, Qwen3.6-35B-A3B Q4_K_M, TTFT 0.8 s, per-request decode.

Measured by

third_party

Reproducible

yes

notes

Lower-RAM (64GB) M5 Max config; same ballpark as the 128GB MLX run, confirming the figure is bandwidth-bound not capacity-bound at this model size.

Lower-RAM (64GB) M5 Max config; same ballpark as the 128GB MLX run, confirming the figure is bandwidth-bound not capacity-bound at this model size.