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:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
96 vs 78
Hardware Fit
94 vs 59
Quality Score
97 vs 86

Hardware

swift-1.5-iq2_xs qwen2.5-coder:32b
MachineGigabyte Technology Co., Ltd. B550M AORUS PRONVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 5 5600X 6-Core ProcessorCortex-X925
Cores1220
RAM47 GB122 GB
GPUAD106 [GeForce RTX 4060 Ti]Device 2e12
OSArch LinuxUbuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance

Performance

swift-1.5-iq2_xs qwen2.5-coder:32b
Tokens/sec60.09.5
First chunk2 ms394 ms
TTFT2.6 s395 ms
Load timeN/A72.1 s
Memory usage0.9 GB26.5 GB
Memory %2%22%

HW Fit Score Breakdown

swift-1.5-iq2_xs

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

qwen2.5-coder:32b

Speed
9/50
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:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View swift-1.5-iq2_xs details | View qwen2.5-coder:32b 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