kwangsuklee/Nanbeige4.1-3B.Q4_K

kwangsuklee/ Nanbeige4.1-3B.Q4_K_M:latest

300 Downloads Updated 2 weeks ago

26.2.27. Nanbeige4.1-3B-Q4 illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors.

tools thinking

ollama run kwangsuklee/Nanbeige4.1-3B.Q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kwangsuklee/Nanbeige4.1-3B.Q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kwangsuklee/Nanbeige4.1-3B.Q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kwangsuklee/Nanbeige4.1-3B.Q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 weeks ago

2 weeks ago

05c8b1009363 · 2.4GB ·

model

archllama

parameters3.93B

quantizationQ4_K_M

2.4GB

params

{ "min_p": 0.01, "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_en

132B

template

{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la

2.9kB

Readme

This model is Nanbeige4.1-3B-Q4. (2.4GB)

Nanbeige4.1-3B-Q4 > Qwen3-32B (Not 3.5 But 3)

Nanbeige4.1-3B-Q8 (4.2GB) https://ollama.com/tomng/nanbeige4.1:3b

GGUF files https://huggingface.co/mradermacher/Nanbeige4.1-3B-GGUF

Original model card https://huggingface.co/Nanbeige/Nanbeige4.1-3B