qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
80 vs 84
Hardware Fit
77 vs 80
Quality Score
81 vs 86
Hardware
qwen3.6:35b-mlx gemma4:26b
MachineMacBook ProSystem manufacturer
CPUApple M5 MaxAMD Ryzen 9 5950X 16-Core Processor
Cores1832
RAM48 GB32 GB
GPUApple M5 MaxNVIDIA GeForce RTX 3090
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx gemma4:26b
Tokens/sec129.8147.6
First chunk77 ms139 ms
TTFT30.0 s30.0 s
Load time1.8 s21.3 s
Memory usage19.7 GB1.7 GB
Memory %41%5%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
gemma4:26b
Speed
50/50
TTFT
0/20
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
gemma4:26b
Reasoning
17/20
Coding
14/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate 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