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
29 vs 84
Hardware Fit
86 vs 82
Quality Score
4 vs 85

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/sec17.927.2
First chunk1010 ms732 ms
TTFT6.4 s8.1 s
Load time9.5 s3.5 s
Memory usage3.0 GB7.1 GB
Memory %40%44%

HW Fit Score Breakdown

qwen3:4b

Speed
50/50
TTFT
8/20
Memory
28/30

gemma4:12b-mlx

Speed
50/50
TTFT
6/20
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
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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