beltranaceves/llama3.1

beltranaceves/ llama3.1

54 Downloads Updated 4 months ago

Quantized variants of llama3.1:8b-instruct-fp16 for the purpose of tesing in ContextAgentBench

tools

ollama run beltranaceves/llama3.1:8b-instruct-q4

curl http://localhost:11434/api/chat \
  -d '{
    "model": "beltranaceves/llama3.1:8b-instruct-q4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='beltranaceves/llama3.1:8b-instruct-q4',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'beltranaceves/llama3.1:8b-instruct-q4',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model beltranaceves/llama3.1:8b-instruct-q4

OpenCode ollama launch opencode --model beltranaceves/llama3.1:8b-instruct-q4

Hermes Agent ollama launch hermes --model beltranaceves/llama3.1:8b-instruct-q4

OpenClaw ollama launch openclaw --model beltranaceves/llama3.1:8b-instruct-q4

Models

View all →

Name

3 models

Size / Usage

Context

Input

llama3.1:8b-instruct-q4

4.9GB · 128K context window · Text · 4 months ago

llama3.1:8b-instruct-q4

4.9GB

128K

Text

llama3.1:8b-instruct-q4-small

4.7GB · 128K context window · Text · 4 months ago

llama3.1:8b-instruct-q4-small

4.7GB

128K

Text

llama3.1:8b-instruct-q8

8.5GB · 128K context window · Text · 4 months ago

llama3.1:8b-instruct-q8

8.5GB

128K

Text

Readme

No readme