llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
63 vs 68
Hardware Fit
100 vs 22
Quality Score
47 vs 88
Hardware
llama3.2:1b qwen3.8:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperSystem manufacturer
CPUCortex-A78AEAMD Ryzen 9 5950X 16-Core Processor
Cores632
RAM7 GB32 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3090
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:1b qwen3.8:latest
Tokens/sec40.210.0
First chunk1087 ms1041 ms
TTFT1.1 s14.3 s
Load time6.2 s22.3 s
Memory usage1.4 GB26.2 GB
Memory %19%82%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
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
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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