Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
77 vs 88
Hardware Fit
90 vs 85
Quality Score
71 vs 89

Hardware

spark-x2.5-4b huihui-qwen3.6-35b…
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD Ryzen 7 4800HAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM15 GB47 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

spark-x2.5-4b huihui-qwen3.6-35b…
Tokens/sec48.937.7
First chunk20 ms18 ms
TTFT168 ms2.9 s
Load timeN/AN/A
Memory usage9.4 GB26.1 GB
Memory %61%56%

HW Fit Score Breakdown

spark-x2.5-4b

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

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

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest