swift-1.5-iq2_xs
LM-STUDIO UNKNOWNNov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
Global Score
96 vs 95
Hardware Fit
94 vs 94
Quality Score
97 vs 96
Hardware
swift-1.5-iq2_xs qwen3-30b-a3b-thin…
MachineGigabyte Technology Co., Ltd. B550M AORUS PROMac Studio
CPUAMD Ryzen 5 5600X 6-Core ProcessorApple M2 Max
Cores1212
RAM47 GB96 GB
GPUAD106 [GeForce RTX 4060 Ti]Apple M2 Max
OSArch LinuxmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced
Performance
swift-1.5-iq2_xs qwen3-30b-a3b-thin…
Tokens/sec60.080.4
First chunk2 ms46 ms
TTFT2.6 s1.8 s
Load timeN/AN/A
Memory usage0.9 GB21.2 GB
Memory %2%22%
HW Fit Score Breakdown
swift-1.5-iq2_xs
Speed
50/50
TTFT
14/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
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
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
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