swift-1.5-iq2_xs
LM-STUDIO UNKNOWNNov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor
gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
96 vs 76
Hardware Fit
94 vs 51
Quality Score
97 vs 87
Hardware
swift-1.5-iq2_xs gemma-3-27b-it-qat
MachineGigabyte Technology Co., Ltd. B550M AORUS PROMac mini
CPUAMD Ryzen 5 5600X 6-Core ProcessorApple M4 Pro
Cores1214
RAM47 GB64 GB
GPUAD106 [GeForce RTX 4060 Ti]Apple M4 Pro
OSArch LinuxmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced
Performance
swift-1.5-iq2_xs gemma-3-27b-it-qat
Tokens/sec60.08.9
First chunk2 ms3976 ms
TTFT2.6 s4.0 s
Load timeN/AN/A
Memory usage0.9 GB15.7 GB
Memory %2%25%
HW Fit Score Breakdown
swift-1.5-iq2_xs
Speed
50/50
TTFT
14/20
Memory
30/30
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
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
gemma-3-27b-it-qat
Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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