qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
61 vs 71
Hardware Fit
69 vs 76
Quality Score
58 vs 69
Hardware
qwen3.5:4b gemma4:12b-mlx
MachineGigabyte Technology Co., Ltd. H170M-D3HMacBook Pro
CPUIntel Core™ i5-6500Apple M1 Pro
Cores410
RAM16 GB16 GB
GPUGP104 [GeForce GTX 1070]Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:4b gemma4:12b-mlx
Tokens/sec35.725.0
First chunk438 ms787 ms
TTFT5.1 s30.0 s
Load time40.1 s4.0 s
Memory usage5.5 GB7.1 GB
Memory %35%45%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
11/20
Memory
8/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
qwen3.5:4b
Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong 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