lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Global Score
60 vs 65
Hardware Fit
80 vs 87
Quality Score
52 vs 56
Hardware
lfm2.5-thinking:1.2b qwen2.5:1.5b
MachineMacBook ProShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M4 ProZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores148
RAM48 GB30 GB
GPUApple M4 ProZX C-1190
OSmacOS 26.4.1Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b qwen2.5:1.5b
Tokens/sec227.016.8
First chunk60 ms941 ms
TTFT30.0 s941 ms
Load time0.7 s0.2 s
Memory usage2.6 GB1.0 GB
Memory %6%3%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen2.5:1.5b
Speed
37/50
TTFT
20/20
Memory
30/30
Quality
lfm2.5-thinking:1.2b
Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong 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