qwen3.6:27b

qwen35 · 27.8B · Q4_K_M

THINKING MODEL

Mac mini (Apple M4 Pro)

24 GB · macOS 15.6.1

Tested on June 25, 2026 · Submitted by Tram

Top 98% Compare

Global Score

20 /100

Not Rec.

Hardware Fit

34/100

Quality

14/100

Get this model

🦙

Ollama

ollama pull qwen3.6:27b

View on Ollama Library

ollama.com/library/qwen3.6

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Mac mini
CPU: Apple M4 Pro
Cores: 12 total (8 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 24 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.6.1
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 10.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.8
First chunk latency Delay before the first streamed chunk arrives from runtime: 1.3 s
Time to first token How fast the model starts responding — lower is better: 30.0 s
Load time Time to load the model into memory before inference: 0.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 18.1 GB (75%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~785

Score breakdown

Speed

22/50

Time to first token

0/20

Memory

12/30

Quality

Reasoning

2/20

Coding

1/20

Instruction following

2/20

Structured output

1/15

Math

2/15

Multilingual

6/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.10
Model format: GGUF
Hardware profile: BALANCED
Result hash: 4c9be9ced280a7aa9cec6780d0d966236a5f1ad4ec31d799b6305b5748ddf4ef

Interpretation

Hardware fit: 34/100. Overall suitability: NOT RECOMMENDED (Global 20/100). 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.

Disqualifiers

Time to first token too high: 30000ms (maximum: 20636ms for BALANCED profile)

Bench Environment

Power: AC CPU load: avg 20% (peak 26%)

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