dhiltgen/olmo-3

dhiltgen/ olmo-3

180 Downloads Updated 3 months ago

tools thinking

ollama run dhiltgen/olmo-3:7b-instruct-fp16-ggml

curl http://localhost:11434/api/chat \
  -d '{
    "model": "dhiltgen/olmo-3:7b-instruct-fp16-ggml",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='dhiltgen/olmo-3:7b-instruct-fp16-ggml',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'dhiltgen/olmo-3:7b-instruct-fp16-ggml',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model dhiltgen/olmo-3:7b-instruct-fp16-ggml

OpenCode

OpenCode ollama launch opencode --model dhiltgen/olmo-3:7b-instruct-fp16-ggml

Hermes Agent

Hermes Agent ollama launch hermes --model dhiltgen/olmo-3:7b-instruct-fp16-ggml

OpenClaw

OpenClaw ollama launch openclaw --model dhiltgen/olmo-3:7b-instruct-fp16-ggml

Models

Name

18 models

Size / Usage

Context

Input

olmo-3:7b-instruct-fp16-ggml

15GB · 64K context window · Text · 3 months ago

olmo-3:7b-instruct-fp16-ggml

15GB

64K

Text

olmo-3:7b-instruct-fp16-llamacpp

15GB · 64K context window · Text · 3 months ago

olmo-3:7b-instruct-fp16-llamacpp

15GB

64K

Text

olmo-3:7b-instruct-q4_K_M-ggml

4.5GB · 64K context window · Text · 3 months ago

olmo-3:7b-instruct-q4_K_M-ggml

4.5GB

64K

Text

olmo-3:7b-instruct-q4_K_M-llamacpp

4.5GB · 64K context window · Text · 3 months ago

olmo-3:7b-instruct-q4_K_M-llamacpp

4.5GB

64K

Text

olmo-3:7b-instruct-q8_0-ggml

7.8GB · 64K context window · Text · 3 months ago

olmo-3:7b-instruct-q8_0-ggml

7.8GB

64K

Text

olmo-3:7b-instruct-q8_0-llamacpp

7.8GB · 64K context window · Text · 3 months ago

olmo-3:7b-instruct-q8_0-llamacpp

7.8GB

64K

Text

olmo-3:7b-think-fp16-ggml

15GB · 64K context window · Text · 3 months ago

olmo-3:7b-think-fp16-ggml

15GB

64K

Text

olmo-3:7b-think-fp16-llamacpp

15GB · 64K context window · Text · 3 months ago

olmo-3:7b-think-fp16-llamacpp

15GB

64K

Text

olmo-3:7b-think-q4_K_M-ggml

4.5GB · 64K context window · Text · 3 months ago

olmo-3:7b-think-q4_K_M-ggml

4.5GB

64K

Text

olmo-3:7b-think-q4_K_M-llamacpp

4.5GB · 64K context window · Text · 3 months ago

olmo-3:7b-think-q4_K_M-llamacpp

4.5GB

64K

Text

olmo-3:7b-think-q8_0-ggml

7.8GB · 64K context window · Text · 3 months ago

olmo-3:7b-think-q8_0-ggml

7.8GB

64K

Text

olmo-3:7b-think-q8_0-llamacpp

7.8GB · 64K context window · Text · 3 months ago

olmo-3:7b-think-q8_0-llamacpp

7.8GB

64K

Text

olmo-3:32b-think-fp16-ggml

64GB · 64K context window · Text · 3 months ago

olmo-3:32b-think-fp16-ggml

64GB

64K

Text

olmo-3:32b-think-fp16-llamacpp

64GB · 64K context window · Text · 3 months ago

olmo-3:32b-think-fp16-llamacpp

64GB

64K

Text

olmo-3:32b-think-q4_K_M-ggml

19GB · 64K context window · Text · 3 months ago

olmo-3:32b-think-q4_K_M-ggml

19GB

64K

Text

olmo-3:32b-think-q4_K_M-llamacpp

19GB · 64K context window · Text · 3 months ago

olmo-3:32b-think-q4_K_M-llamacpp

19GB

64K

Text

olmo-3:32b-think-q8_0-ggml

34GB · 64K context window · Text · 3 months ago

olmo-3:32b-think-q8_0-ggml

34GB

64K

Text

olmo-3:32b-think-q8_0-llamacpp

34GB · 64K context window · Text · 3 months ago

olmo-3:32b-think-q8_0-llamacpp

34GB

64K

Text

Readme

No readme