Instructions to use Brooooooklyn/Qwen3.5-9B-unsloth-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Brooooooklyn/Qwen3.5-9B-unsloth-mlx 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("Brooooooklyn/Qwen3.5-9B-unsloth-mlx")

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 Brooooooklyn/Qwen3.5-9B-unsloth-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Brooooooklyn/Qwen3.5-9B-unsloth-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Brooooooklyn/Qwen3.5-9B-unsloth-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Brooooooklyn/Qwen3.5-9B-unsloth-mlx 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 "Brooooooklyn/Qwen3.5-9B-unsloth-mlx"

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 Brooooooklyn/Qwen3.5-9B-unsloth-mlx

Run Hermes

hermes

MLX LM

How to use Brooooooklyn/Qwen3.5-9B-unsloth-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Brooooooklyn/Qwen3.5-9B-unsloth-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Brooooooklyn/Qwen3.5-9B-unsloth-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Brooooooklyn/Qwen3.5-9B-unsloth-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Brooooooklyn commited on Mar 24

Commit

c3cd551

verified ·

1 Parent(s): f60dfb8

Add Unsloth GGUF comparison table to README

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -96,6 +96,17 @@ Based on Unsloth's per-tensor 99.9% KLD analysis (sorted by sensitivity, worst
 AWQ-correctable projections (q/k/v, in_proj_qkv/z) are quantized at 5-bit with imatrix AWQ pre-scaling via `input_layernorm`. Non-AWQ-correctable projections (o_proj, out_proj) are kept at bf16 — their inputs come from attention/GDN computation, not from a norm layer, so AWQ cannot be applied. imatrix is **required** for the unsloth recipe.
 ## Architecture
 Qwen3.5-9B is a decoder-only transformer with a hybrid attention design:

 AWQ-correctable projections (q/k/v, in_proj_qkv/z) are quantized at 5-bit with imatrix AWQ pre-scaling via `input_layernorm`. Non-AWQ-correctable projections (o_proj, out_proj) are kept at bf16 — their inputs come from attention/GDN computation, not from a norm layer, so AWQ cannot be applied. imatrix is **required** for the unsloth recipe.
+### Comparison with Unsloth GGUF (UD-Q3_K_XL)
+| Tensor | Unsloth UD-Q3_K_XL | Ours | Gap |
+|---|---|---|---|
+| attn q/k/v | Q5_K + imatrix | 5-bit affine + AWQ | Small (AWQ compensates) |
+| in_proj_qkv/z | Q5_K + imatrix | 5-bit affine + AWQ | Small |
+| o_proj | Q5_K + imatrix | bf16 | We're larger but lossless |
+| out_proj | Q5_K + imatrix | bf16 | We're larger but lossless |
+| FFN gate/up | Q3_K + imatrix | 3-bit affine + AWQ | Moderate (K-quant > affine at 3-bit) |
+| FFN down | Q4_K + imatrix | 4-bit affine + AWQ | Small |
 ## Architecture
 Qwen3.5-9B is a decoder-only transformer with a hybrid attention design: