deepscaler:1.5b

OLLAMA GGUF

qwen2 · 1.8B · F16

Good

Oct 11, 2026 · AMD Ryzen 5 5500

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score

64 vs 83

Hardware Fit

98 vs 96

Quality Score

49 vs 78

Hardware

deepscaler:1.5b google/gemma-4-e4b

MachineMicrosoft WSLASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH

CPUAMD Ryzen 5 5500AMD Ryzen 9 8940HX

Cores1232

RAM8 GB15 GB

GPUIntegrated / UnknownNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M

OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Home Single Language 10.0.26200

Archx64x64

Power Modeunknownbalanced

Performance

deepscaler:1.5b google/gemma-4-e4b

Tokens/sec104.635.9

First chunk849 ms9 ms

TTFT850 ms182 ms

Load time10.5 sN/A

Memory usage3.0 GB6.5 GB

Memory %40%43%

HW Fit Score Breakdown

deepscaler:1.5b

Speed

50/50

TTFT

20/20

Memory

28/30

google/gemma-4-e4b

Speed

49/50

TTFT

20/20

Memory

27/30

Quality

deepscaler:1.5b

Reasoning

10/20

Coding

6/20

Instruction

10/20

Structured

7/15

Math

11/15

Multilingual

5/10

Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak

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 deepscaler:1.5b 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