Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
77 vs 81
Hardware Fit
90 vs 100
Quality Score
71 vs 73

Hardware

spark-x2.5-4b llama-3.1-8b-instr…
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMASUS
CPUAMD Ryzen 7 4800HAMD Ryzen 5 5500
Cores1612
RAM15 GB31 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Pro 10.0.26200Nobara Linux 43
Archx64x64
Power Modebalancedperformance

Performance

spark-x2.5-4b llama-3.1-8b-instr…
Tokens/sec48.935.6
First chunk20 ms52 ms
TTFT168 ms256 ms
Load timeN/AN/A
Memory usage9.4 GB8.6 GB
Memory %61%28%

HW Fit Score Breakdown

spark-x2.5-4b

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

llama-3.1-8b-instruct

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

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

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View spark-x2.5-4b details | View llama-3.1-8b-instr… 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