qwen3.8-27b-mlx

qwen3_5 · 27B · 8bit

MacBook Pro (Apple M5 Max)

64 GB · macOS 27.0

Tested on August 17, 2026 · Submitted by itxjobe

Top 81% Compare

Global Score

59 /100

Marginal

Hardware Fit

63/100

Quality

58/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: MacBook Pro
CPU: Apple M5 Max
Cores: 18 threads (6 cores)
Frequency: 2.4 GHz
RAM: 64 GB LPDDR5
GPU: Apple M5 Max
OS: macOS 27.0
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 18.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.5
First chunk latency Delay before the first streamed chunk arrives from runtime: 4 ms
Time to first token How fast the model starts responding — lower is better: 530 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 38.5 GB (60%)
Total tokens Total number of tokens generated across all benchmark prompts: 1743

Score breakdown

Speed

23/50

Time to first token

20/20

Memory

20/30

Quality

Reasoning

19/20

Coding

14/20

Instruction following

6/20

Structured output

1/15

Math

13/15

Multilingual

5/10

Category levels

Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

Metadata

Spec version: 0.2.1
Runtime: LM Studio
Model format: MLX
Hardware profile: HIGH-END
Result hash: d31f353f19a7d894e0d1cc98e8eb21471aa28e036a261797aaf4a82cead0a4a1

Interpretation

Hardware fit: 63/100. Overall suitability: MARGINAL (Global 59/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Weak, Structured Output: Poor, Math: Strong, Multilingual: Weak.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Bench Environment

Power: AC CPU load: avg 11% (peak 14%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest