Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
62 vs 72
Hardware Fit
35 vs 71
Quality Score
73 vs 72

Hardware

qwen3.5-4b-mlx gemma4:e2b
MachineMac miniDell Inc. Inspiron 15 3530
CPUApple M4 ProIntel Gen Intel® Core™ i7-1355U
Cores1412
RAM64 GB31 GB
GPUApple M4 ProRaptor Lake-P [Iris Xe Graphics]
OSmacOS 15.7.4cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5-4b-mlx gemma4:e2b
Tokens/sec0.010.8
First chunk5548 ms1408 ms
TTFT5.5 s1.4 s
Load timeN/A6.0 s
Memory usage2.9 GB7.2 GB
Memory %5%23%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

gemma4:e2b

Speed
21/50
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

gemma4:e2b

Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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