llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
74 vs 76
Hardware Fit
99 vs 51
Quality Score
63 vs 87
Hardware
llama3.2:3b qwen3-coder:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperDell Inc. Inspiron 15 3530
CPUCortex-A78AEIntel Gen Intel® Core™ i7-1355U
Cores612
RAM7 GB31 GB
GPUIntegrated / UnknownRaptor Lake-P [Iris Xe Graphics]
OSUbuntu 22.04.5 LTScachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
llama3.2:3b qwen3-coder:latest
Tokens/sec21.17.6
First chunk1032 ms2037 ms
TTFT1.0 s2.0 s
Load time8.4 s8.7 s
Memory usage2.4 GB18.9 GB
Memory %32%61%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
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
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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