dhiltgen/llama3

dhiltgen/ llama3

326 Downloads Updated 2 months ago

ollama run dhiltgen/llama3:8b-instruct-fp16-ggml

curl http://localhost:11434/api/chat \
  -d '{
    "model": "dhiltgen/llama3:8b-instruct-fp16-ggml",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='dhiltgen/llama3:8b-instruct-fp16-ggml',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'dhiltgen/llama3:8b-instruct-fp16-ggml',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

24 models

Size / Usage

Context

Input

llama3:8b-instruct-fp16-ggml

16GB · 8K context window · Text · 3 months ago

llama3:8b-instruct-fp16-ggml

16GB

Text

llama3:8b-instruct-fp16-llamacpp

16GB · 8K context window · Text · 3 months ago

llama3:8b-instruct-fp16-llamacpp

16GB

Text

llama3:8b-instruct-q4_K_M-ggml

4.9GB · 8K context window · Text · 3 months ago

llama3:8b-instruct-q4_K_M-ggml

4.9GB

Text

llama3:8b-instruct-q4_K_M-llamacpp

4.9GB · 8K context window · Text · 3 months ago

llama3:8b-instruct-q4_K_M-llamacpp

4.9GB

Text

llama3:8b-instruct-q8_0-ggml

8.5GB · 8K context window · Text · 3 months ago

llama3:8b-instruct-q8_0-ggml

8.5GB

Text

llama3:8b-instruct-q8_0-llamacpp

8.5GB · 8K context window · Text · 3 months ago

llama3:8b-instruct-q8_0-llamacpp

8.5GB

Text

llama3:8b-text-fp16-ggml

16GB · 8K context window · Text · 2 months ago

llama3:8b-text-fp16-ggml

16GB

Text

llama3:8b-text-fp16-llamacpp

16GB · 8K context window · Text · 2 months ago

llama3:8b-text-fp16-llamacpp

16GB

Text

llama3:8b-text-q4_K_M-ggml

4.9GB · 8K context window · Text · 2 months ago

llama3:8b-text-q4_K_M-ggml

4.9GB

Text

llama3:8b-text-q4_K_M-llamacpp

4.9GB · 8K context window · Text · 2 months ago

llama3:8b-text-q4_K_M-llamacpp

4.9GB

Text

llama3:8b-text-q8_0-ggml

8.5GB · 8K context window · Text · 2 months ago

llama3:8b-text-q8_0-ggml

8.5GB

Text

llama3:8b-text-q8_0-llamacpp

8.5GB · 8K context window · Text · 2 months ago

llama3:8b-text-q8_0-llamacpp

8.5GB

Text

llama3:70b-instruct-fp16-ggml

141GB · 8K context window · Text · 3 months ago

llama3:70b-instruct-fp16-ggml

141GB

Text

llama3:70b-instruct-fp16-llamacpp

141GB · 8K context window · Text · 3 months ago

llama3:70b-instruct-fp16-llamacpp

141GB

Text

llama3:70b-instruct-q4_K_M-ggml

43GB · 8K context window · Text · 3 months ago

llama3:70b-instruct-q4_K_M-ggml

43GB

Text

llama3:70b-instruct-q4_K_M-llamacpp

43GB · 8K context window · Text · 3 months ago

llama3:70b-instruct-q4_K_M-llamacpp

43GB

Text

llama3:70b-instruct-q8_0-ggml

75GB · 8K context window · Text · 3 months ago

llama3:70b-instruct-q8_0-ggml

75GB

Text

llama3:70b-instruct-q8_0-llamacpp

75GB · 8K context window · Text · 3 months ago

llama3:70b-instruct-q8_0-llamacpp

75GB

Text

llama3:70b-text-fp16-ggml

141GB · 8K context window · Text · 2 months ago

llama3:70b-text-fp16-ggml

141GB

Text

llama3:70b-text-fp16-llamacpp

141GB · 8K context window · Text · 2 months ago

llama3:70b-text-fp16-llamacpp

141GB

Text

llama3:70b-text-q4_K_M-ggml

43GB · 8K context window · Text · 2 months ago

llama3:70b-text-q4_K_M-ggml

43GB

Text

llama3:70b-text-q4_K_M-llamacpp

43GB · 8K context window · Text · 2 months ago

llama3:70b-text-q4_K_M-llamacpp

43GB

Text

llama3:70b-text-q8_0-ggml

75GB · 8K context window · Text · 2 months ago

llama3:70b-text-q8_0-ggml

75GB

Text

llama3:70b-text-q8_0-llamacpp

75GB · 8K context window · Text · 2 months ago

llama3:70b-text-q8_0-llamacpp

75GB

Text

Readme

No readme