Back to leaderboard

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
84 vs 59
Hardware Fit
82 vs 63
Quality Score
85 vs 58

Hardware

gemma4:12b-mlx qwen3.8-27b-mlx
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M5 Max
Cores1018
RAM16 GB64 GB
GPUApple M2 ProApple M5 Max
OSmacOS 26.5macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:12b-mlx qwen3.8-27b-mlx
Tokens/sec27.218.3
First chunk732 ms4 ms
TTFT8.1 s530 ms
Load time3.5 sN/A
Memory usage7.1 GB38.5 GB
Memory %44%60%

HW Fit Score Breakdown

gemma4:12b-mlx

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

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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