Instructions to use nikimori/Qwen3.5-2B-Base-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikimori/Qwen3.5-2B-Base-6bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("nikimori/Qwen3.5-2B-Base-6bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use nikimori/Qwen3.5-2B-Base-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimori/Qwen3.5-2B-Base-6bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nikimori/Qwen3.5-2B-Base-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nikimori/Qwen3.5-2B-Base-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nikimori/Qwen3.5-2B-Base-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nikimori/Qwen3.5-2B-Base-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nikimori/Qwen3.5-2B-Base-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use nikimori/Qwen3.5-2B-Base-6bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimori/Qwen3.5-2B-Base-6bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default nikimori/Qwen3.5-2B-Base-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nikimori/Qwen3.5-2B-Base-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimori/Qwen3.5-2B-Base-6bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nikimori/Qwen3.5-2B-Base-6bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.5-2B-Base, 6-bit MLX

Qwen/Qwen3.5-2B-Base converted to MLX with mlx_lm.convert -q --q-bits 6 --q-group-size 64 (mlx-lm 0.31.3, affine). The weights are otherwise unchanged, and the license is the upstream one (Apache-2.0).

Converted for Pretype, where it is the completion model for 8 GB Macs. On Pretype's 5,649-row, 17-language autocomplete set it gets the first word right on 19% of all rows: ahead of the 4-bit build (17%, paired McNemar p < 0.001) and tied with an 8-bit conversion (19%, 1.9 GB), at 1.5 GB.

from mlx_lm import load, generate
model, tokenizer = load("<this repo>")
print(generate(model, tokenizer, prompt="The quick brown fox", max_tokens=20))

Downloads last month: 566

Safetensors

Model size

2B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

6-bit

Model tree for nikimori/Qwen3.5-2B-Base-6bit

Base model

Qwen/Qwen3.5-2B-Base

Quantized

(34)

this model