Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
83 vs 76
Hardware Fit
96 vs 51
Quality Score
78 vs 87

Hardware

google/gemma-4-e4b qwen3-coder:latest
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHDell Inc. Inspiron 15 3530
CPUAMD Ryzen 9 8940HXIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM15 GB31 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MRaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Home Single Language 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

google/gemma-4-e4b qwen3-coder:latest
Tokens/sec35.97.6
First chunk9 ms2037 ms
TTFT182 ms2.0 s
Load timeN/A8.7 s
Memory usage6.5 GB18.9 GB
Memory %43%61%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3-coder:latest

Speed
13/50
TTFT
18/20
Memory
20/30

Quality

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

qwen3-coder:latest

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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