Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Nov 4, 2026 · Intel Core™ i7-9700

Global Score
70 vs 71
Hardware Fit
73 vs 90
Quality Score
68 vs 63

Hardware

llama3.1:8b-instru… llama3.2:3b
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… llama3.2:3b
Tokens/sec6.513.0
First chunk950 ms536 ms
TTFT950 ms536 ms
Load time11.5 s82.5 s
Memory usage4.4 GB2.4 GB
Memory %38%15%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

llama3.2:3b

Speed
40/50
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

llama3.2:3b

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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