Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

gemma4:e4b

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
70 vs 87
Hardware Fit
73 vs 100
Quality Score
68 vs 81

Hardware

llama3.1:8b-instru… gemma4:e4b
Machine—Gigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUC1-ProIntel Core™ i5-14400F
Cores016
RAM11 GB32 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5060 Ti
OSunknown unknownMicrosoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… gemma4:e4b
Tokens/sec6.582.1
First chunk950 ms64 ms
TTFT950 ms64 ms
Load time11.5 s6.1 s
Memory usage4.4 GB3.0 GB
Memory %38%9%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

gemma4:e4b

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

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

gemma4:e4b

Reasoning
14/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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