gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
84 vs 55
Hardware Fit
82 vs 87
Quality Score
85 vs 41
Hardware
gemma4:12b-mlx qwen3.5-0.8b-mlx
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx qwen3.5-0.8b-mlx
Tokens/sec27.268.2
First chunk732 ms3268 ms
TTFT8.1 s3.3 s
Load time3.5 sN/A
Memory usage7.1 GB0.6 GB
Memory %44%2%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
13/20
Memory
24/30
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
qwen3.5-0.8b-mlx
Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest