lmstudio-community/gemma-4-e4b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

Global Score

77 vs 65

Hardware Fit

68 vs 96

Quality Score

81 vs 52

Hardware

lmstudio-community… richardyoung/qwyth…

MachineDocker ContainerMac mini

CPUIntel Gen Intel® Core™ i9-11900HApple M4 Pro

Cores1612

RAM15 GB24 GB

GPUTigerLake-H GT1 [UHD Graphics]Apple M4 Pro

OSUbuntu 26.04 LTSmacOS 15.6.1

Archx64arm64

Power Modeperformancebalanced

Performance

lmstudio-community… richardyoung/qwyth…

Tokens/sec11.425.3

First chunk28 ms397 ms

TTFT2.2 s397 ms

Load time6.8 s6.3 s

Memory usage0.6 GB8.3 GB

Memory %4%34%

HW Fit Score Breakdown

lmstudio-community/gemm…

Speed

21/50

TTFT

17/20

Memory

30/30

richardyoung/qwythos-9b…

Speed

47/50

TTFT

20/20

Memory

29/30

Quality

lmstudio-community/gemm…

Reasoning

14/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

richardyoung/qwythos-9b…

Reasoning

18/20

Coding

13/20

Instruction

6/20

Structured

0/15

Math

14/15

Multilingual

1/10

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

View lmstudio-community… details | View richardyoung/qwyth… 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