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

LM-STUDIO GGUF

gemma4 · Q4_0

Good

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

ornith-1.5-35b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Aug 21, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score

77 vs 85

Hardware Fit

68 vs 88

Quality Score

81 vs 84

Hardware

lmstudio-community… ornith-1.5-35b

MachineDocker ContainerMicro-Star International Co., Ltd. MS-7E51

CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 7 9700X 8-Core Processor

Cores1616

RAM15 GB31 GB

GPUTigerLake-H GT1 [UHD Graphics]NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics

OSUbuntu 26.04 LTSMicrosoft Windows 11 Pro 10.0.26200

Archx64x64

Power Modeperformancebalanced

Performance

lmstudio-community… ornith-1.5-35b

Tokens/sec11.480.4

First chunk28 ms24 ms

TTFT2.2 s231 ms

Load time6.8 sN/A

Memory usage0.6 GB20.2 GB

Memory %4%65%

HW Fit Score Breakdown

lmstudio-community/gemm…

Speed

21/50

TTFT

17/20

Memory

30/30

ornith-1.5-35b

Speed

50/50

TTFT

20/20

Memory

18/30

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

ornith-1.5-35b

Reasoning

14/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

View lmstudio-community… details | View ornith-1.5-35b 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