llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
stablelm-2-zephyr-1.6b
LM-STUDIO GGUFstablelm · 1.6B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
74 vs 35
Hardware Fit
99 vs 61
Quality Score
63 vs 24
Hardware
llama3.2:3b stablelm-2-zephyr-…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20BUS00700
CPUCortex-A78AEIntel Core™ i5-5300U
Cores64
RAM7 GB16 GB
GPUIntegrated / UnknownIntel(R) HD Graphics 5500
OSUbuntu 22.04.5 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b stablelm-2-zephyr-…
Tokens/sec21.16.5
First chunk1032 ms3080 ms
TTFT1.0 s3.1 s
Load time8.4 sN/A
Memory usage2.4 GB1.0 GB
Memory %32%6%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
stablelm-2-zephyr-1.6b
Speed
23/50
TTFT
16/20
Memory
22/30
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
stablelm-2-zephyr-1.6b
Reasoning
2/20
Coding
2/20
Instruction
8/20
Structured
6/15
Math
2/15
Multilingual
4/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
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