Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
81 vs 71
Hardware Fit
98 vs 76
Quality Score
74 vs 69

Hardware

qwen3.5:4b gemma4:12b-mlx
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M1 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b gemma4:12b-mlx
Tokens/sec93.725.0
First chunk249 ms787 ms
TTFT249 ms30.0 s
Load time10.1 s4.0 s
Memory usage2.9 GB7.1 GB
Memory %38%45%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
20/20
Memory
28/30

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

Quality

qwen3.5:4b

Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View gemma4:12b-mlx details

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