Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

Global Score
70 vs 81
Hardware Fit
73 vs 84
Quality Score
68 vs 79

Hardware

llama3.1:8b-instru… google/gemma-4-e4b
Machine—GMKtec EVO-X3
CPUC1-ProAMD RYZEN AI MAX+ 395
Cores032
RAM11 GB120 GB
GPUIntegrated / UnknownAMD Radeon(TM) 8060S Graphics
OSunknown unknownMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… google/gemma-4-e4b
Tokens/sec6.547.3
First chunk950 ms23 ms
TTFT950 ms1.9 s
Load time11.5 sN/A
Memory usage4.4 GB13.2 GB
Memory %38%11%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

google/gemma-4-e4b

Speed
44/50
TTFT
10/20
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

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
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