Yarflam/SmolLM3-Q4KM

Yarflam/ SmolLM3-Q4KM:latest

44 Downloads Updated 2 months ago

Thinking model - efficient

ollama run Yarflam/SmolLM3-Q4KM

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Yarflam/SmolLM3-Q4KM",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Yarflam/SmolLM3-Q4KM',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Yarflam/SmolLM3-Q4KM',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 months ago

2 months ago

708d818fbbcd · 1.9GB ·

model

archsmollm3

parameters3.08B

quantizationQ4_K_M

1.9GB

params

{ "num_ctx": 16384, "stop": [ "<|im_end|>", "<|im_start|>" ], "tempe

106B

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ range .Messages }}<|im_start|

169B

Readme

Original model from https://huggingface.co/ggml-org/SmolLM3-3B-GGUF.

Thinking model – efficient when you don’t have enough GPU on your computer. 🤪