qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
Global Score
80 vs 87
Hardware Fit
77 vs 75
Quality Score
81 vs 92
Hardware
qwen3.6:35b-mlx gemma4:latest
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E47
CPUApple M5 MaxAMD Ryzen 9 9950X 16-Core Processor
Cores1832
RAM48 GB125 GB
GPUApple M5 MaxAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx gemma4:latest
Tokens/sec129.842.4
First chunk77 ms472 ms
TTFT30.0 s3.8 s
Load time1.8 s0.3 s
Memory usage19.7 GB12.3 GB
Memory %41%10%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
gemma4:latest
Speed
40/50
TTFT
5/20
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:latest
Reasoning
19/20
Coding
18/20
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