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

Libraries

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

# 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-S 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-S"

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-S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use airagrp/Qwen3.8-27B-mlx-nvfp4-S 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-S"

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-S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use airagrp/Qwen3.8-27B-mlx-nvfp4-S 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-S"

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-S" \
  --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"

This repository contains Qwen/Qwen3.8-27B converted to MLX format with a mixed-precision quantization recipe, using 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)	nvfp4 (group_size=16, bits=4)
Linear (GDN) attention `in_proj_*` / `out_proj` (48 layers)	nvfp4 (group_size=16, bits=4)
Token embeddings (`embed_tokens`)	bfloat16
Output head (`lm_head`)	bfloat16
MTP head	bfloat16
Vision tower	bfloat16

Effective size: ~21 GB (5.9 bits per weight), base model is ~54 GB in bfloat16.
Quantized modules: nvfp4 (group_size=16, bits=4); bfloat16 modules are stored as-is. Per-module precision is detected from the presence of .scales tensors.

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

pip install mlx-vlm

import mlx_vlm

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

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

Use with MLX directly

Load with the standard MLX safetensors layout; quantized weights use nvfp4 (group_size=16, bits=4).

Citations / license

Apache-2.0. Refer to the original model card for architecture details, benchmarks, and usage guidelines.

Quality benchmarks

Perplexity and KL divergence on the WikiText-2 raw test split (297,053 tokens, 2048-token windows, fresh KV cache per window), measured against the bf16 reference (Qwen3.8-27B-mlx).

Model	Size (GiB)	PPL (lower = better)	ΔPPL vs bf16	KLD vs bf16 (nats/token, lower = better)
`Qwen3.8-27B-mlx` (bf16 reference)	51.75	6.935	—	—
`Qwen3.8-27B-mlx-nvfp4-S`	19.15	7.024	+0.088	0.0573
`Qwen3.8-27B-QAT-NVFP4`	19.15	7.298	+0.362	0.0753
`Qwen3.8-27B-mlx-nvfp4-M`	21.57	6.983	+0.048	0.0490
`Qwen3.8-27B-mlx-nvfp4-L`	22.31	6.987	+0.051	0.0407
`Qwen3.8-27B-mlx-nvfp4-XL`	28.84	7.024	+0.089	0.0382
`Qwen3.8-27B-mlx-mxfp8-M`	29.78	6.893	-0.042	0.0068
`Qwen3.8-27B-mlx-mxfp8-L`	34.79	6.937	+0.002	0.0046
`Qwen3.8-27B-mlx-mxfp8-XL`	36.31	6.937	+0.002	0.0037

KLD = mean per-token D_KL(p_bf16 ‖ p_model) over the full vocabulary — how much the quantized model's next-token distribution drifts from bf16.
Data: wikitext-2-raw-v1 test split, SHA-256 c5b5caea5bd655cb…; tokenizer: Qwen3.8-27B-mlx; mlx-vlm 0.6.17.
Benchmarked 2026-09-03 with benchmark_ppl_kld.py (2048-token streaming windows, all positions except the first of each window scored).