qwen3.5-27b

qwen35 · 27B · Q4_K_M

THINKING MODEL

Mac mini (Apple M4 Pro)

64 GB · macOS 15.7.4

Tested on March 6, 2026

Top 98% Compare

Global Score

26 /100

Not Rec.

Hardware Fit

63/100

Quality

10/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Mac mini
CPU: Apple M4 Pro
Cores: 14 total (10 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 64 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.7.4
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 9.5
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 1.1 s
Time to first token How fast the model starts responding — lower is better: 1.1 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 16.3 GB (25%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429

Score breakdown

Speed

13/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

0/20

Coding

0/20

Instruction following

2/20

Structured output

0/15

Math

1/15

Multilingual

7/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: GGUF
Hardware profile: HIGH-END
Result hash: ac3a20b1eae7bf8a37cec4134c263a8312ce01cfa1d3f8dc4b2241863bb2ab20

Interpretation

Hardware fit: 63/100. Overall suitability: NOT RECOMMENDED (Global 26/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Poor, Multilingual: Adequate. Warning: model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Warnings

Model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Bench Environment

Power: AC CPU load: avg 23% (peak 28%)

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