llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
74 vs 77
Hardware Fit
99 vs 75
Quality Score
63 vs 78
Hardware
llama3.2:3b qwen3.5:9b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEIntel Gen Intel® Core™ i7-13700K
Cores624
RAM7 GB64 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3070
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
llama3.2:3b qwen3.5:9b
Tokens/sec21.130.5
First chunk1032 ms291 ms
TTFT1.0 s291 ms
Load time8.4 s4.8 s
Memory usage2.4 GB8.8 GB
Memory %32%14%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3.5:9b
Speed
34/50
TTFT
20/20
Memory
21/30
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
qwen3.5:9b
Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate 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