qwen3.6:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
20 vs 74
Hardware Fit
34 vs 99
Quality Score
14 vs 63
Hardware
qwen3.6:27b llama3.2:3b
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 ProCortex-A78AE
Cores126
RAM24 GB7 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 15.6.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.6:27b llama3.2:3b
Tokens/sec10.621.1
First chunk1344 ms1032 ms
TTFT30.0 s1.0 s
Load time0.2 s8.4 s
Memory usage18.1 GB2.4 GB
Memory %75%32%
HW Fit Score Breakdown
qwen3.6:27b
Speed
22/50
TTFT
0/20
Memory
12/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.6:27b
Reasoning
2/20
Coding
1/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
6/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
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
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