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 · Apple M1 Max
Global Score
74 vs 53
Hardware Fit
99 vs 72
Quality Score
63 vs 45
Hardware
llama3.2:3b qwen3.5:9b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Max
Cores610
RAM7 GB32 GB
GPUIntegrated / UnknownApple M1 Max
OSUbuntu 22.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:3b qwen3.5:9b
Tokens/sec21.118.6
First chunk1032 ms403 ms
TTFT1.0 s10.2 s
Load time8.4 s4.3 s
Memory usage2.4 GB9.1 GB
Memory %32%28%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3.5:9b
Speed
38/50
TTFT
4/20
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
qwen3.5:9b
Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak 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