MiMo-V2.6-Flash-RL-MLX-4bit-MTP

Instructions to use sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP")
config = load_config("sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP"

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": "sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP 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 "sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP"

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 sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP"

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 "sayyidfareed/MiMo-V2.6-Flash-RL-MLX-4bit-MTP" \
  --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"

MiMo-V2.6-Flash-RL-MLX-4bit-MTP / dflash /config.json

sayyidfareed

ashxhart

Duplicate from Vontra/MiMo-V2.6-Flash-RL-MLX-4bit-MTP

9ca55c6 7 days ago

Raw History Blame Contribute Delete

1.24 kB

	{
	"architectures": [
	"DFlashDraftModel"
	],
	"model_type": "qwen3",
	"auto_map": {
	"AutoModel": "dflash.DFlashDraftModel"
	},
	"hidden_size": 4096,
	"intermediate_size": 16384,
	"num_hidden_layers": 5,
	"num_attention_heads": 64,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"v_head_dim": 128,
	"partial_rotary_factor": 0.5,
	"block_size": 8,
	"dflash_config": {
	"target_layer_ids": [
	0,
	11,
	23,
	35,
	47
	],
	"mask_token_id": 151675,
	"num_anchors": 4096,
	"block_size": 8,
	"loss_decay_gamma": 7.0,
	"attention_value_scale": 0.612,
	"attention_sink_bias": true
	},
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"sliding_window": 1024,
	"use_sliding_window": true,
	"is_causal": false,
	"num_target_layers": 48,
	"target_hidden_size": 4096,
	"vocab_size": 152576,
	"max_position_embeddings": 1048576,
	"rope_theta": 10000.0,
	"rms_norm_eps": 1e-06,
	"torch_dtype": "bfloat16",
	"hidden_act": "silu",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"add_swa_attention_sink_bias": true,
	"tie_word_embeddings": false,
	"use_cache": true
	}