Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

prism-ml/bonsai-27b

LM-STUDIO GGUF

qwen35 · 27B · Q1_0

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
77 vs 81
Hardware Fit
90 vs 95
Quality Score
71 vs 75

Hardware

spark-x2.5-4b prism-ml/bonsai-27b
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUAMD Ryzen 7 4800HAMD Ryzen 9 8940HX
Cores1632
RAM15 GB15 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

spark-x2.5-4b prism-ml/bonsai-27b
Tokens/sec48.933.6
First chunk20 ms20 ms
TTFT168 ms409 ms
Load timeN/AN/A
Memory usage9.4 GB5.3 GB
Memory %61%35%

HW Fit Score Breakdown

spark-x2.5-4b

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

prism-ml/bonsai-27b

Speed
46/50
TTFT
20/20
Memory
29/30

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

prism-ml/bonsai-27b

Reasoning
17/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate 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