Instructions to use airagrp/Qwen3.8-27B-QAT-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use airagrp/Qwen3.8-27B-QAT-NVFP4 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("airagrp/Qwen3.8-27B-QAT-NVFP4")
config = load_config("airagrp/Qwen3.8-27B-QAT-NVFP4")

# 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 airagrp/Qwen3.8-27B-QAT-NVFP4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "airagrp/Qwen3.8-27B-QAT-NVFP4"

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": "airagrp/Qwen3.8-27B-QAT-NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use airagrp/Qwen3.8-27B-QAT-NVFP4 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 "airagrp/Qwen3.8-27B-QAT-NVFP4"

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 airagrp/Qwen3.8-27B-QAT-NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use airagrp/Qwen3.8-27B-QAT-NVFP4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "airagrp/Qwen3.8-27B-QAT-NVFP4"

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 "airagrp/Qwen3.8-27B-QAT-NVFP4" \
  --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"

airagrp commited on about 19 hours ago

Commit

21f71a5

verified ·

1 Parent(s): 1bf5dce

Merge MTP tensors into index (native omlx MTP detection; no mtplx contract)

Browse files

Files changed (1) hide show

model.safetensors.index.json +16 -1

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 19709532640
     },
     "weight_map": {
         "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
@@ -1350,6 +1350,21 @@
         "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
         "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
         "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
         "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
         "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
         "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",

 {
     "metadata": {
+        "total_size": 20558931424
     },
     "weight_map": {
         "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
         "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
         "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
         "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+        "language_model.mtp.fc.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.input_layernorm.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.mlp.down_proj.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.mlp.gate_proj.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.mlp.up_proj.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.post_attention_layernorm.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.self_attn.k_norm.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.self_attn.k_proj.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.self_attn.o_proj.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.self_attn.q_norm.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.self_attn.q_proj.weight": "mtp.safetensors",
+        "language_model.mtp.layers.0.self_attn.v_proj.weight": "mtp.safetensors",
+        "language_model.mtp.norm.weight": "mtp.safetensors",
+        "language_model.mtp.pre_fc_norm_embedding.weight": "mtp.safetensors",
+        "language_model.mtp.pre_fc_norm_hidden.weight": "mtp.safetensors",
         "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
         "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
         "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",