Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
32 vs 91
Hardware Fit
98 vs 96
Quality Score
4 vs 89

Hardware

qwen3:4b gemma4:12b-mlx
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M2 Pro
Cores610
RAM7 GB16 GB
GPUIntegrated / UnknownApple M2 Pro
OSUbuntu 22.04.5 LTSmacOS 26.5
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3:4b gemma4:12b-mlx
Tokens/sec17.924.7
First chunk950 ms610 ms
TTFT950 ms610 ms
Load time9.7 s3.6 s
Memory usage3.0 GB7.1 GB
Memory %40%45%

HW Fit Score Breakdown

qwen3:4b

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

gemma4:12b-mlx

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

Quality

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

gemma4:12b-mlx

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b 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