qwen3.5:27b

qwen35 · 27.8B · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026

Top 19% Compare

Global Score

75 /100

Good

Hardware Fit

67/100

Quality

79/100

Get this model

🦙

Ollama

ollama pull qwen3.5:27b

View on Ollama Library

ollama.com/library/qwen3.5

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 4.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
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: 13.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 22.7 GB (71%)
Total tokens Total number of tokens generated across all benchmark prompts: 469

Score breakdown

Speed

7/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

16/20

Coding

17/20

Instruction following

9/20

Structured output

15/15

Math

12/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.5
Model format: GGUF
Hardware profile: BALANCED
Result hash: 52c11313f2675179487563e0415f3cf275ab637b9a5bfa5002cc239660fae93d

Interpretation

Hardware fit: 67/100. Overall suitability: GOOD (Global 74/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Weak, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running