Instructions to use Youssofal/Qwen3.5-4B-Optimized-MTPLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Youssofal/Qwen3.5-4B-Optimized-MTPLX 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("Youssofal/Qwen3.5-4B-Optimized-MTPLX")

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
LM Studio

Pi new

How to use Youssofal/Qwen3.5-4B-Optimized-MTPLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Youssofal/Qwen3.5-4B-Optimized-MTPLX"

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": "Youssofal/Qwen3.5-4B-Optimized-MTPLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Youssofal/Qwen3.5-4B-Optimized-MTPLX 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 "Youssofal/Qwen3.5-4B-Optimized-MTPLX"

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 Youssofal/Qwen3.5-4B-Optimized-MTPLX

Run Hermes

hermes

MLX LM

How to use Youssofal/Qwen3.5-4B-Optimized-MTPLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Youssofal/Qwen3.5-4B-Optimized-MTPLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Youssofal/Qwen3.5-4B-Optimized-MTPLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Youssofal/Qwen3.5-4B-Optimized-MTPLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3.5-4B-Optimized-MTPLX / config.json

Youssofal

Add files using upload-large-folder tool

b8825d6 verified 20 days ago

raw

history blame contribute delete

4.34 kB

	{
	"architectures": [
	"Qwen3_5ForConditionalGeneration"
	],
	"image_token_id": 248056,
	"library_name": "mlx",
	"mlx_lm_extra_tensors": {
	"mtp_file": "mtp.safetensors",
	"mtp_tensor_count": 29
	},
	"model_type": "qwen3_5",
	"mtplx_mtp_quantization": {
	"bits": 4,
	"description": "Official Qwen3.5-4B MTP head with layer-0 attention/MLP linears quantized to MLX affine INT4 group64; mtp.fc and norms stay BF16.",
	"group_size": 64,
	"mode": "affine",
	"policy": "cyankiwi",
	"prequantized": true
	},
	"mtplx_policy": {
	"description": "mlx-community/Qwen3.5-4B-MLX-8bit trunk plus official Qwen3.5-4B MTP sidecar stored as body-int4 for MTPLX speed testing.",
	"local_official_source": "/Users/youssof/.mtplx/sources/Qwen--Qwen3.5-4B",
	"local_trunk_source": "/Users/youssof/.mtplx/sources/mlx-community--Qwen3.5-4B-MLX-8bit",
	"mtp_quantization": {
	"bits": 4,
	"group_size": 64,
	"linears": [
	"mtp.layers.0.mlp.down_proj",
	"mtp.layers.0.mlp.gate_proj",
	"mtp.layers.0.mlp.up_proj",
	"mtp.layers.0.self_attn.k_proj",
	"mtp.layers.0.self_attn.o_proj",
	"mtp.layers.0.self_attn.q_proj",
	"mtp.layers.0.self_attn.v_proj"
	],
	"mode": "affine",
	"norms": "bf16"
	},
	"name": "qwen35-4b-q8-official-mtp-body-int4-speed",
	"quantization_family": "mlx-affine-q8",
	"source": "Qwen/Qwen3.5-4B",
	"trunk_quantization": {
	"bits": 8,
	"group_size": 64,
	"mode": "affine"
	},
	"trunk_source": "mlx-community/Qwen3.5-4B-MLX-8bit"
	},
	"quantization": {
	"bits": 8,
	"group_size": 64,
	"mode": "affine"
	},
	"quantization_config": {
	"bits": 8,
	"group_size": 64,
	"mode": "affine"
	},
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 9216,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"model_type": "qwen3_5_text",
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 16,
	"num_hidden_layers": 32,
	"num_key_value_heads": 4,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"tie_word_embeddings": true,
	"use_cache": true,
	"vocab_size": 248320
	},
	"tie_word_embeddings": true,
	"transformers_version": "4.57.0.dev0",
	"video_token_id": 248057,
	"vision_config": {
	"deepstack_visual_indexes": [],
	"depth": 24,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1024,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "qwen3_5",
	"num_heads": 16,
	"num_position_embeddings": 2304,
	"out_hidden_size": 2560,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 248054,
	"vision_start_token_id": 248053
	}