Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

Apr 3, 2026 · Apple M4

Global Score
62 vs 85
Hardware Fit
35 vs 77
Quality Score
73 vs 89

Hardware

qwen3.5-4b-mlx gemma4:26b
MachineMac miniMac mini
CPUApple M4 ProApple M4
Cores1410
RAM64 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx gemma4:26b
Tokens/sec0.024.5
First chunk5548 ms1481 ms
TTFT5.5 s1.5 s
Load timeN/A24.7 s
Memory usage2.9 GB20.3 GB
Memory %5%85%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

gemma4:26b

Speed
49/50
TTFT
20/20
Memory
8/30

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

gemma4:26b

Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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