Back to leaderboard

swift-1.5-iq2_xs

LM-STUDIO UNKNOWN
Excellent

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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
96 vs 68
Hardware Fit
94 vs 93
Quality Score
97 vs 57

Hardware

swift-1.5-iq2_xs google/gemma-4-e4b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROLENOVO 82JQ
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD Ryzen 7 5800H
Cores1216
RAM47 GB16 GB
GPUAD106 [GeForce RTX 4060 Ti]NVIDIA GeForce RTX 3060 Laptop GPU
OSArch LinuxMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modelow-powerbalanced

Performance

swift-1.5-iq2_xs google/gemma-4-e4b
Tokens/sec60.026.2
First chunk2 ms17 ms
TTFT2.6 s572 ms
Load timeN/AN/A
Memory usage0.9 GB6.5 GB
Memory %2%41%

HW Fit Score Breakdown

swift-1.5-iq2_xs

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

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

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

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View swift-1.5-iq2_xs details | View google/gemma-4-e4b 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