Back to leaderboard

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score
84 vs 32
Hardware Fit
82 vs 98
Quality Score
85 vs 4

Hardware

gemma4:12b-mlx qwen3:4b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M2 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M2 ProIntegrated / Unknown
OSmacOS 26.5Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:12b-mlx qwen3:4b
Tokens/sec27.217.9
First chunk732 ms950 ms
TTFT8.1 s950 ms
Load time3.5 s9.7 s
Memory usage7.1 GB3.0 GB
Memory %44%40%

HW Fit Score Breakdown

gemma4:12b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

qwen3:4b

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

Quality

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

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
View gemma4:12b-mlx details | View qwen3:4b 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