Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score
65 vs 76
Hardware Fit
88 vs 46
Quality Score
55 vs 89

Hardware

qwen3.5-2b-mlx gemma4:31b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M4 Max
Cores1416
RAM64 GB64 GB
GPUApple M4 ProApple M4 Max
OSmacOS 15.7.4macOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx gemma4:31b
Tokens/sec48.922.4
First chunk4208 ms565 ms
TTFT4.2 s30.0 s
Load timeN/A6.9 s
Memory usage1.6 GB43.9 GB
Memory %3%69%

HW Fit Score Breakdown

qwen3.5-2b-mlx

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

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

Quality

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
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