llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
63 vs 88
Hardware Fit
100 vs 80
Quality Score
47 vs 91
Hardware
llama3.2:1b qwopus3.6-27b-code…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEAMD Ryzen 7 7800X3D 8-Core Processor
Cores616
RAM7 GB31 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 22.04.5 LTScachyos rolling
Archarm64x64
Power Modebalancedperformance
Performance
llama3.2:1b qwopus3.6-27b-code…
Tokens/sec40.280.8
First chunk1087 ms6 ms
TTFT1.1 s226 ms
Load time6.2 sN/A
Memory usage1.4 GB24.6 GB
Memory %19%81%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
Quality
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
qwopus3.6-27b-coder-com…
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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