Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
61 vs 83
Hardware Fit
69 vs 96
Quality Score
58 vs 78

Hardware

qwen3.5:4b google/gemma-4-e4b
MachineGigabyte Technology Co., Ltd. H170M-D3HASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUIntel Core™ i5-6500AMD Ryzen 9 8940HX
Cores432
RAM16 GB15 GB
GPUGP104 [GeForce GTX 1070]NVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:4b google/gemma-4-e4b
Tokens/sec35.735.9
First chunk438 ms9 ms
TTFT5.1 s182 ms
Load time40.1 sN/A
Memory usage5.5 GB6.5 GB
Memory %35%43%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

google/gemma-4-e4b

Speed
49/50
TTFT
20/20
Memory
27/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b 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