llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Global Score
74 vs 65
Hardware Fit
99 vs 87
Quality Score
63 vs 56
Hardware
llama3.2:3b qwen2.5:1.5b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUCortex-A78AEZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores68
RAM7 GB30 GB
GPUIntegrated / UnknownZX C-1190
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b qwen2.5:1.5b
Tokens/sec21.116.8
First chunk1032 ms941 ms
TTFT1.0 s941 ms
Load time8.4 s0.2 s
Memory usage2.4 GB1.0 GB
Memory %32%3%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
qwen2.5:1.5b
Speed
37/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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