Back to leaderboard

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

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

Hardware

qwen3-coder:latest google/gemma-4-e4b
MachineDell Inc. Inspiron 15 3530ASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUIntel Gen Intel® Core™ i7-1355UAMD Ryzen 9 8940HX
Cores1232
RAM31 GB15 GB
GPURaptor Lake-P [Iris Xe Graphics]NVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OScachyos rollingMicrosoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3-coder:latest google/gemma-4-e4b
Tokens/sec7.635.9
First chunk2037 ms9 ms
TTFT2.0 s182 ms
Load time8.7 sN/A
Memory usage18.9 GB6.5 GB
Memory %61%43%

HW Fit Score Breakdown

qwen3-coder:latest

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

google/gemma-4-e4b

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

Quality

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

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-coder:latest 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