gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Global Score
71 vs 65
Hardware Fit
76 vs 87
Quality Score
69 vs 56
Hardware
gemma4:12b-mlx qwen2.5:1.5b
MachineMacBook ProShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M1 ProZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores108
RAM16 GB30 GB
GPUApple M1 ProZX C-1190
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx qwen2.5:1.5b
Tokens/sec25.016.8
First chunk787 ms941 ms
TTFT30.0 s941 ms
Load time4.0 s0.2 s
Memory usage7.1 GB1.0 GB
Memory %45%3%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
qwen2.5:1.5b
Speed
37/50
TTFT
20/20
Memory
30/30
Quality
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
qwen2.5:1.5b
Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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