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"

Qwen3.8-27B-QUASAR-NVFP4-mlx

MLX conversion of QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4, a 4-bit NVFP4 (W4A4) quantization-aware-trained build of Qwen/Qwen3.8-27B where all 496 linear layers (self-attention, gated delta-net, and MLP) are NVFP4. Converted from the source compressed-tensors nvfp4-pack-quantized checkpoint to the MLX-native nvfp4 layout for the omlx / mlx-vlm runtime on Apple silicon.

~19.15 GiB: 4 weight shards (18.36 GiB) + mtp.safetensors (MTP draft head, 15 tensors, 810 MiB).
1695 tensors: 496 packed NVFP4 weights (uint32) + 496 E4M3 scales (uint8)
- 703 BF16 (embeddings, lm_head, vision tower, norms, conv1d, A_log, dt_bias)
- the 15-tensor MTP head.

Conversion notes

MLX's nvfp4 kernel is single-level and does not carry the per-tensor global scale, so the two-level source scaling is folded into the per-group E4M3 scales: the E2M1 codes are kept bit-exact and each per-group scale is stored as E4M3(decode(weight_scale) / weight_global_scale). This single re-rounding of the (much smaller) scale tensor is the only precision change versus the source; the packed 4-bit weights themselves are byte-identical.

MTP norm weights carry the MLX +1.0 RMSNorm shift; the MTP head is a separate mtp.safetensors side file.

Produced with convert_vllm_nvfp4_to_mlx.py.

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).