Back to leaderboard

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

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

Hardware

qwen2.5:72b google/gemma-4-e4b
MachineNVIDIA NVIDIA_DGX_SparkASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUCortex-X925AMD Ryzen 9 8940HX
Cores2032
RAM122 GB15 GB
GPUDevice 2e12NVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5:72b google/gemma-4-e4b
Tokens/sec4.435.9
First chunk529 ms9 ms
TTFT529 ms182 ms
Load time49.7 sN/A
Memory usage54.0 GB6.5 GB
Memory %44%43%

HW Fit Score Breakdown

qwen2.5:72b

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

google/gemma-4-e4b

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

Quality

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

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
View qwen2.5:72b 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