qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
65 vs 63
Hardware Fit
87 vs 100
Quality Score
56 vs 47
Hardware
qwen2.5:1.5b llama3.2:1b
MachineShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRBNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUZHAOXIN KaiXian KX-7000 KaiXian KX-7000Cortex-A78AE
Cores86
RAM30 GB7 GB
GPUZX C-1190Integrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26100Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5:1.5b llama3.2:1b
Tokens/sec16.840.2
First chunk941 ms1087 ms
TTFT941 ms1.1 s
Load time0.2 s6.2 s
Memory usage1.0 GB1.4 GB
Memory %3%19%
HW Fit Score Breakdown
qwen2.5:1.5b
Speed
37/50
TTFT
20/20
Memory
30/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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