Back to leaderboard

ornith-1.5-35b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
85 vs 68
Hardware Fit
88 vs 93
Quality Score
84 vs 57

Hardware

ornith-1.5-35b google/gemma-4-e4b
MachineMicro-Star International Co., Ltd. MS-7E51LENOVO 82JQ
CPUAMD Ryzen 7 9700X 8-Core ProcessorAMD Ryzen 7 5800H
Cores1616
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

ornith-1.5-35b google/gemma-4-e4b
Tokens/sec80.426.2
First chunk24 ms17 ms
TTFT231 ms572 ms
Load timeN/AN/A
Memory usage20.2 GB6.5 GB
Memory %65%41%

HW Fit Score Breakdown

ornith-1.5-35b

Speed
50/50
TTFT
20/20
Memory
18/30

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

Quality

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

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View ornith-1.5-35b 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