qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 6, 2026 · Apple M4 Pro
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
53 vs 88
Hardware Fit
89 vs 86
Quality Score
38 vs 89
Hardware
qwen3.5-0.8b-mlx gemma4:12b-it-qat
MachineMac miniMac mini
CPUApple M4 ProApple M4 Pro
Cores1412
RAM64 GB24 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-0.8b-mlx gemma4:12b-it-qat
Tokens/sec52.930.0
First chunk4013 ms686 ms
TTFT4.0 s7.1 s
Load timeN/A5.4 s
Memory usage0.6 GB7.1 GB
Memory %1%30%
HW Fit Score Breakdown
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
9/20
Memory
30/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
qwen3.5-0.8b-mlx
Reasoning
7/20
Coding
2/20
Instruction
12/20
Structured
10/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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