Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
62 vs 66
Hardware Fit
35 vs 91
Quality Score
73 vs 55

Hardware

qwen3.5-4b-mlx qwen3.8-27b-mlx
MachineMac miniMacBook Pro
CPUApple M4 ProApple M5 Max
Cores1418
RAM64 GB64 GB
GPUApple M4 ProApple M5 Max
OSmacOS 15.7.4macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx qwen3.8-27b-mlx
Tokens/sec0.033.2
First chunk5548 ms7 ms
TTFT5.5 s311 ms
Load timeN/AN/A
Memory usage2.9 GB0.5 GB
Memory %5%1%

HW Fit Score Breakdown

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

qwen3.8-27b-mlx

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

Quality

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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

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