qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 26, 2026 · Apple M1 Pro
Global Score
80 vs 91
Hardware Fit
77 vs 88
Quality Score
81 vs 92
Hardware
qwen3.6:35b-mlx gemma4:e4b-it-q8_0
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM48 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx gemma4:e4b-it-q8_0
Tokens/sec129.830.0
First chunk77 ms311 ms
TTFT30.0 s6.2 s
Load time1.8 s6.9 s
Memory usage19.7 GB5.0 GB
Memory %41%31%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
8/20
Memory
30/30
Quality
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
gemma4:e4b-it-q8_0
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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