gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

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

deepseek-r1-distill-qwen-14b-mlx

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

Global Score

72 vs 36

Hardware Fit

71 vs 53

Quality Score

72 vs 28

Hardware

gemma4:e2b deepseek-r1-distil…

MachineDell Inc. Inspiron 15 3530Mac mini

CPUIntel Gen Intel® Core™ i7-1355UApple M4

Cores1210

RAM31 GB24 GB

GPURaptor Lake-P [Iris Xe Graphics]Apple M4

OScachyos rollingmacOS 26.3

Archx64arm64

Power Modelow-powerbalanced

Performance

gemma4:e2b deepseek-r1-distil…

Tokens/sec10.810.3

First chunk1408 ms27 ms

TTFT1.4 s20.7 s

Load time6.0 s15.4 s

Memory usage7.2 GB1.0 GB

Memory %23%4%

HW Fit Score Breakdown

gemma4:e2b

Speed

21/50

TTFT

20/20

Memory

30/30

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

Quality

gemma4:e2b

Reasoning

10/20

Coding

16/20

Instruction

14/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

deepseek-r1-distill-qwe…

Reasoning

3/20

Coding

6/20

Instruction

6/20

Structured

3/15

Math

2/15

Multilingual

8/10

Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Strong

View gemma4:e2b details | View deepseek-r1-distil… 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