Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Nov 4, 2026 · Intel Core™ i7-9700

Global Score
70 vs 75
Hardware Fit
73 vs 84
Quality Score
68 vs 71

Hardware

llama3.1:8b-instru… phi4-mini:latest
Machine—VMware, Inc. VMware Virtual Platform
CPUC1-ProIntel Core™ i7-9700
Cores04
RAM11 GB16 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSunknown unknownUbuntu 24.04.5 LTS
Archarm64x64
Power Modeunknownunknown

Performance

llama3.1:8b-instru… phi4-mini:latest
Tokens/sec6.510.8
First chunk950 ms643 ms
TTFT950 ms643 ms
Load time11.5 s31.5 s
Memory usage4.4 GB2.9 GB
Memory %38%19%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

phi4-mini:latest

Speed
34/50
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

phi4-mini:latest

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate 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