qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 24, 2026 · Apple M2
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
53 vs 63
Hardware Fit
81 vs 62
Quality Score
41 vs 63
Hardware
qwen3.5:4b-mlx gemma4:12b
MachineMac miniMacBook Pro
CPUApple M2Apple M1 Pro
Cores810
RAM8 GB16 GB
GPUApple M2Apple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:4b-mlx gemma4:12b
Tokens/sec24.815.3
First chunk317 ms1142 ms
TTFT7.4 s30.0 s
Load time0.0 s5.4 s
Memory usage3.9 GB7.6 GB
Memory %49%47%
HW Fit Score Breakdown
qwen3.5:4b-mlx
Speed
50/50
TTFT
6/20
Memory
25/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
qwen3.5:4b-mlx
Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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