qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
mlx-community/stablelm-2-zephyr-1_6b-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
80 vs 50
Hardware Fit
77 vs 100
Quality Score
81 vs 29
Hardware
qwen3.6:35b-mlx mlx-community/stab…
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM48 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx mlx-community/stab…
Tokens/sec129.893.6
First chunk77 ms166 ms
TTFT30.0 s166 ms
Load time1.8 sN/A
Memory usage19.7 GB0.7 GB
Memory %41%2%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
mlx-community/stablelm-…
Speed
50/50
TTFT
20/20
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
mlx-community/stablelm-…
Reasoning
7/20
Coding
2/20
Instruction
9/20
Structured
3/15
Math
4/15
Multilingual
4/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Weak
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