Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
46 vs 83
Hardware Fit
61 vs 96
Quality Score
40 vs 78

Hardware

llama3.1:8b google/gemma-4-e4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUCortex-A78AEAMD Ryzen 9 8940HX
Cores632
RAM7 GB15 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

llama3.1:8b google/gemma-4-e4b
Tokens/sec7.835.9
First chunk1625 ms9 ms
TTFT1.6 s182 ms
Load time21.8 sN/A
Memory usage5.2 GB6.5 GB
Memory %71%43%

HW Fit Score Breakdown

llama3.1:8b

Speed
26/50
TTFT
20/20
Memory
15/30

google/gemma-4-e4b

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

Quality

llama3.1:8b

Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak 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 llama3.1:8b 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