Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
84 vs 77
Hardware Fit
66 vs 90
Quality Score
92 vs 71

Hardware

qwen3.8:27b spark-x2.5-4b
MachineNVIDIA NVIDIA_DGX_SparkASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUCortex-X925AMD Ryzen 7 4800H
Cores2016
RAM122 GB15 GB
GPUDevice 2e12AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

qwen3.8:27b spark-x2.5-4b
Tokens/sec29.448.9
First chunk306 ms20 ms
TTFT4.8 s168 ms
Load time5.3 sN/A
Memory usage16.2 GB9.4 GB
Memory %13%61%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

spark-x2.5-4b

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

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.8:27b details | View spark-x2.5-4b 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