Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
83 vs 75
Hardware Fit
96 vs 50
Quality Score
78 vs 86

Hardware

google/gemma-4-e4b qwen2.5:72b
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 9 8940HXCortex-X925
Cores3220
RAM15 GB122 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MDevice 2e12
OSMicrosoft Windows 11 Home Single Language 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

google/gemma-4-e4b qwen2.5:72b
Tokens/sec35.94.4
First chunk9 ms529 ms
TTFT182 ms529 ms
Load timeN/A49.7 s
Memory usage6.5 GB54.0 GB
Memory %43%44%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

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

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-4-e4b details | View qwen2.5:72b 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