Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

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
83 vs 85
Hardware Fit
96 vs 88
Quality Score
78 vs 84

Hardware

google/gemma-4-e4b ornith-1.5-35b
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 9 8940HXAMD Ryzen 7 9700X 8-Core Processor
Cores3216
RAM15 GB31 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Home Single Language 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b ornith-1.5-35b
Tokens/sec35.980.4
First chunk9 ms24 ms
TTFT182 ms231 ms
Load timeN/AN/A
Memory usage6.5 GB20.2 GB
Memory %43%65%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
49/50
TTFT
20/20
Memory
27/30

ornith-1.5-35b

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

Quality

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

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

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