gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jun 5, 2026 · AMD Ryzen 7 5800H
qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 25, 2026 · Apple M1 Pro
Global Score
89 vs 68
Hardware Fit
83 vs 91
Quality Score
92 vs 58
Hardware
gemma4:latest qwen3.5:4b-mlx
MachineLENOVO 82JQMacBook Pro
CPUAMD Ryzen 7 5800HApple M1 Pro
Cores1610
RAM16 GB16 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M1 Pro
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:latest qwen3.5:4b-mlx
Tokens/sec46.342.2
First chunk824 ms201 ms
TTFT3.8 s4.4 s
Load time21.0 s0.0 s
Memory usage8.9 GB3.8 GB
Memory %56%24%
HW Fit Score Breakdown
gemma4:latest
Speed
50/50
TTFT
11/20
Memory
22/30
qwen3.5:4b-mlx
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
gemma4:latest
Reasoning
18/20
Coding
19/20
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
qwen3.5:4b-mlx
Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate 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