swift-1.5-iq2_xs
LM-STUDIO UNKNOWNNov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
96 vs 74
Hardware Fit
94 vs 99
Quality Score
97 vs 63
Hardware
swift-1.5-iq2_xs llama3.2:3b
MachineGigabyte Technology Co., Ltd. B550M AORUS PRONVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 5 5600X 6-Core ProcessorCortex-A78AE
Cores126
RAM47 GB7 GB
GPUAD106 [GeForce RTX 4060 Ti]Integrated / Unknown
OSArch LinuxUbuntu 22.04.5 LTS
Archx64arm64
Power Modelow-powerbalanced
Performance
swift-1.5-iq2_xs llama3.2:3b
Tokens/sec60.021.1
First chunk2 ms1032 ms
TTFT2.6 s1.0 s
Load timeN/A8.4 s
Memory usage0.9 GB2.4 GB
Memory %2%32%
HW Fit Score Breakdown
swift-1.5-iq2_xs
Speed
50/50
TTFT
14/20
Memory
30/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
swift-1.5-iq2_xs
Reasoning
20/20
Coding
19/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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