Instructions to use airagrp/Qwen3.8-27B-MLX-nvfp4-mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use airagrp/Qwen3.8-27B-MLX-nvfp4-mixed 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-MLX-nvfp4-mixed")
config = load_config("airagrp/Qwen3.8-27B-MLX-nvfp4-mixed")

# 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-MLX-nvfp4-mixed 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-MLX-nvfp4-mixed"

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-MLX-nvfp4-mixed"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use airagrp/Qwen3.8-27B-MLX-nvfp4-mixed 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-MLX-nvfp4-mixed"

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-MLX-nvfp4-mixed

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use airagrp/Qwen3.8-27B-MLX-nvfp4-mixed 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-MLX-nvfp4-mixed"

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-MLX-nvfp4-mixed" \
  --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"

Qwen3.8-27B-MLX-nvfp4-mixed / README.md

airagrp

mixed nvfp4/bf16 MLX conversion of Qwen/Qwen3.8-27B (mlx-vlm 0.6.17)

ba3ba10 verified 7 days ago

preview code

Raw

History Blame

2.45 kB

	---
	library_name: mlx
	license: apache-2.0
	pipeline_tag: image-text-to-text
	base_model: Qwen/Qwen3.8-27B
	language: en
	tags:
	- mlx
	- mlx-vlm
	- nvfp4
	- mixed-precision
	- qwen3_5
	- multimodal
	- vision
	- video
	- text-generation
	- mtp
	- speculative-decoding
	---
	This repository contains [`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B) converted to MLX format with a mixed-precision quantization recipe, using [mlx-vlm](https://github.com/Blaizzy/mlx-vlm) 0.6.17.

	## Quantization recipe

	\| Module \| Precision \|
	\|---\|---\|
	\| MLP `gate_proj` / `up_proj` / `down_proj` (64 layers) \| nvfp4 (group_size=16, bits=4) \|
	\| Full attention `q_proj` / `k_proj` / `v_proj` / `o_proj` (16 layers) \| bfloat16 \|
	\| Linear (GDN) attention `in_proj_*` / `out_proj` (48 layers) \| bfloat16 \|
	\| Token embeddings (`embed_tokens`) \| bfloat16 \|
	\| Output head (`lm_head`) \| bfloat16 \|
	\| MTP head \| bfloat16 \|
	\| Vision tower \| bfloat16 \|

	- Effective size: ~31 GB (8.9 bits per weight), base model is ~54 GB in bfloat16.
	- Quantized modules are stored as packed nvfp4 weights (E2M1 codes, 8 per uint32) with per-16 E4M3 block scales; bfloat16 modules are stored as-is. Per-module precision is detected from the presence of `.scales` tensors; the global mode is set in `config.json` (`quantization.mode = "nvfp4"`).

	## MTP

	The native MTP head is merged into this checkpoint as `language_model.mtp.*` tensors (15 tensors, bfloat16, norms in the MLX +1 convention), stored in `mtp.safetensors` and referenced from `model.safetensors.index.json` — it is not a separate drafter model. Use it for speculative decoding (`--draft-kind mtp` in mlx-vlm) or ignore it; base inference is unaffected.

	## Use with mlx-vlm

	```bash
	pip install mlx-vlm
	```

	```python
	import mlx_vlm

	model, processor = mlx_vlm.load("airagrp/Qwen3.8-27B-MLX-nvfp4-mixed")
	response, _ = mlx_vlm.generate(
	model,
	processor,
	prompts="In one sentence, what is MLX?",
	max_tokens=64,
	)
	print(response)
	```

	```bash
	mlx_vlm.generate --model airagrp/Qwen3.8-27B-MLX-nvfp4-mixed --prompt "In one sentence, what is MLX?" --max-tokens 64
	```

	## Use with MLX directly

	Load with the standard MLX safetensors layout; weights use the MLX nvfp4 block-scale format (`group_size=16`, `bits=4`).

	## Citations / license

	Apache-2.0. Refer to the [original model card](https://huggingface.co/Qwen/Qwen3.8-27B) for architecture details, benchmarks, and usage guidelines.