Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 22, 2026 · Apple M1 Pro

Global Score
66 vs 69
Hardware Fit
91 vs 85
Quality Score
55 vs 62

Hardware

qwen3.8-27b-mlx qwen3.5:4b
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 27.0macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx qwen3.5:4b
Tokens/sec33.236.9
First chunk7 ms474 ms
TTFT311 ms6.9 s
Load timeN/A2.9 s
Memory usage0.5 GB5.3 GB
Memory %1%33%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

qwen3.5:4b

Speed
50/50
TTFT
6/20
Memory
29/30

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest