unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score

82 vs 83

Hardware Fit

88 vs 96

Quality Score

80 vs 78

Hardware

unsloth-phi-4 google/gemma-4-e4b

MachineMac miniASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH

CPUApple M4 ProAMD Ryzen 9 8940HX

Cores1432

RAM64 GB15 GB

GPUApple M4 ProNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M

OSmacOS 15.7.4Microsoft Windows 11 Home Single Language 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

unsloth-phi-4 google/gemma-4-e4b

Tokens/sec27.435.9

First chunk457 ms9 ms

TTFT457 ms182 ms

Load timeN/AN/A

Memory usage7.7 GB6.5 GB

Memory %12%43%

HW Fit Score Breakdown

unsloth-phi-4

Speed

38/50

TTFT

20/20

Memory

30/30

google/gemma-4-e4b

Speed

49/50

TTFT

20/20

Memory

27/30

Quality

unsloth-phi-4

Reasoning

15/20

Coding

19/20

Instruction

14/20

Structured

13/15

Math

9/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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 unsloth-phi-4 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