Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
78 vs 68
Hardware Fit
86 vs 93
Quality Score
74 vs 57

Hardware

qwen3:8b google/gemma-4-e4b
Machine—LENOVO 82JQ
CPUAMD Ryzen 9 3900X 12-Core ProcessorAMD Ryzen 7 5800H
Cores2416
RAM64 GB16 GB
GPUNVIDIA GeForce RTX 4060 TiNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:8b google/gemma-4-e4b
Tokens/sec48.526.2
First chunk202 ms17 ms
TTFT4.3 s572 ms
Load time4.2 sN/A
Memory usage5.5 GB6.5 GB
Memory %9%41%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View qwen3:8b details | View google/gemma-4-e4b 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