Back to leaderboard

swift-1.5-iq2_xs

LM-STUDIO UNKNOWN
Excellent

Nov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor

qwen2.5-coder:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
96 vs 73
Hardware Fit
94 vs 100
Quality Score
97 vs 61

Hardware

swift-1.5-iq2_xs qwen2.5-coder: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 qwen2.5-coder:3b
Tokens/sec60.021.3
First chunk2 ms969 ms
TTFT2.6 s969 ms
Load timeN/A6.6 s
Memory usage0.9 GB2.0 GB
Memory %2%27%

HW Fit Score Breakdown

swift-1.5-iq2_xs

Speed
50/50
TTFT
14/20
Memory
30/30

qwen2.5-coder:3b

Speed
50/50
TTFT
20/20
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

qwen2.5-coder:3b

Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View swift-1.5-iq2_xs details | View qwen2.5-coder:3b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest