qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 24, 2026 · Apple M2
gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
Global Score
53 vs 87
Hardware Fit
82 vs 75
Quality Score
41 vs 92
Hardware
qwen3.5:4b-mlx gemma4:latest
MachineMac miniMicro-Star International Co., Ltd. MS-7E47
CPUApple M2AMD Ryzen 9 9950X 16-Core Processor
Cores832
RAM8 GB125 GB
GPUApple M2AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5:4b-mlx gemma4:latest
Tokens/sec24.742.4
First chunk302 ms472 ms
TTFT7.4 s3.8 s
Load time3.2 s0.3 s
Memory usage3.8 GB12.3 GB
Memory %47%10%
HW Fit Score Breakdown
qwen3.5:4b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
Quality
qwen3.5:4b-mlx
Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate 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