Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
77 vs 74
Hardware Fit
90 vs 100
Quality Score
71 vs 63

Hardware

spark-x2.5-4b llama3.2:3b
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMMacBook Air
CPUAMD Ryzen 7 4800HApple M4
Cores1610
RAM15 GB32 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

spark-x2.5-4b llama3.2:3b
Tokens/sec48.944.1
First chunk20 msN/A
TTFT168 ms178 ms
Load timeN/A0.8 s
Memory usage9.4 GB7.0 GB
Memory %61%22%

HW Fit Score Breakdown

spark-x2.5-4b

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

llama3.2:3b

Speed
40/50
TTFT
30/20
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

llama3.2:3b

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View spark-x2.5-4b details | View llama3.2:3b 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