doomgrave/phi-4

doomgrave/ phi-4

229 Downloads Updated 11 months ago

phi4:14b, with working tools, quantized to Q2_K and Q3_K_S for GPU with 8gb Vram or less.

tools

ollama run doomgrave/phi-4

curl http://localhost:11434/api/chat \
  -d '{
    "model": "doomgrave/phi-4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='doomgrave/phi-4',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'doomgrave/phi-4',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model doomgrave/phi-4

Codex ollama launch codex --model doomgrave/phi-4

OpenCode ollama launch opencode --model doomgrave/phi-4

OpenClaw ollama launch openclaw --model doomgrave/phi-4

Models

View all →

Name

3 models

Size

Context

Input

phi-4:latest

6.5GB · 16K context window · Text · 11 months ago

phi-4:latest

6.5GB

16K

Text

phi-4:14b-tools-Q2_K

5.5GB · 16K context window · Text · 11 months ago

phi-4:14b-tools-Q2_K

5.5GB

16K

Text

phi-4:14b-tools-Q3_K_S

6.5GB · 16K context window · Text · 11 months ago

phi-4:14b-tools-Q3_K_S

6.5GB

16K

Text

Readme

No readme