Back to leaderboard

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jun 5, 2026 · AMD Ryzen 7 5800H

opencoder-1.5b-instruct

LM-STUDIO GGUF

llama · 1.5B · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
89 vs 44
Hardware Fit
83 vs 52
Quality Score
92 vs 40

Hardware

gemma4:latest opencoder-1.5b-ins…
MachineLENOVO 82JQLENOVO 20BUS00700
CPUAMD Ryzen 7 5800HIntel Core™ i5-5300U
Cores164
RAM16 GB16 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUIntel(R) HD Graphics 5500
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

gemma4:latest opencoder-1.5b-ins…
Tokens/sec46.34.8
First chunk824 ms4870 ms
TTFT3.8 s4.9 s
Load time21.0 sN/A
Memory usage8.9 GB1.3 GB
Memory %56%8%

HW Fit Score Breakdown

gemma4:latest

Speed
50/50
TTFT
11/20
Memory
22/30

opencoder-1.5b-instruct

Speed
18/50
TTFT
11/20
Memory
23/30

Quality

gemma4:latest

Reasoning
18/20
Coding
19/20
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

opencoder-1.5b-instruct

Reasoning
3/20
Coding
15/20
Instruction
7/20
Structured
9/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Weak

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