llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
76 vs 28
Hardware Fit
100 vs 66
Quality Score
65 vs 11
Hardware
llama3.2:latest phi-1_5
MachineMicro-Star International Co., Ltd. MS-7B79LENOVO 20BUS00700
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Core™ i5-5300U
Cores124
RAM16 GB16 GB
GPUNVIDIA GeForce GTX 1080Intel(R) HD Graphics 5500
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
llama3.2:latest phi-1_5
Tokens/sec57.06.9
First chunk264 ms3040 ms
TTFT264 ms3.0 s
Load time9.7 sN/A
Memory usage2.6 GB1.4 GB
Memory %16%9%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
15/20
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
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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