qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
80 vs 72
Hardware Fit
77 vs 99
Quality Score
81 vs 61
Hardware
qwen3.6:35b-mlx mlx-community/gemm…
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/gemm…
Tokens/sec129.886.3
First chunk77 ms253 ms
TTFT30.0 s253 ms
Load time1.8 sN/A
Memory usage19.7 GB1.1 GB
Memory %41%4%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
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/gemma-3-1…
Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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