Instructions to use mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth")
model = AutoModelForMultimodalLM.from_pretrained("mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth

SGLang

How to use mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth with Docker Model Runner:
```
docker model run hf.co/mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth
```

Keural Nova v1.2 — NVFP4 (unsloth mixed-precision recipe)

Mixed-precision NVFP4 quantization of Keural Nova v1.2, by MKD, for high-throughput serving on NVIDIA Blackwell via vLLM.

Replicates the unsloth/Qwen3.6-35B-A3B-NVFP4 recipe — a dynamic mixed FP8/FP4 scheme that keeps accuracy-sensitive layers at higher precision. This is the most accuracy-preserving of our NVFP4 builds. (A pure-NVFP4 variant is at Keural-Nova-v1.2-experimental-NVFP4.)

67 GB (bf16) → 24.8 GB — slightly larger than pure NVFP4 because sensitive layers stay FP8.
Format: compressed-tensors / mixed-precision → served natively by vLLM.

The recipe (exactly unsloth's)

Precision	Layers
FP8 (8-bit)	attention (q/k/v/o), linear-attn projections (in_proj_qkv/z, out_proj), lm_head, last 8 layers' experts (32–39)
FP4 (NVFP4, 4-bit)	the first 32 layers' experts + shared experts (the bulk)
High-precision (bf16)	linear-attn in_proj_a/b/norm, router gates (`mlp.gate`, `shared_expert_gate`), vision tower, MTP

Verified coverage: layer-0 experts FP4, layer-32 experts FP8, all listed sensitive layers bf16.

⚠️ Hardware

FP4 tensor cores exist only on Blackwell (B200 / GB200 / RTX 50xx) — serve there for the speed/memory benefit (Hopper lacks FP4 kernels).

Serving (vLLM on Blackwell)

vllm serve mkd-hossain/Keural-Nova-v1.2-experimental-NVFP4-unsloth \
  --served-model-name Keural-Nova-v1.2 \
  --tensor-parallel-size 2 --max-model-len 262144 \
  --tool-call-parser qwen3_xml --enable-auto-tool-choice

Non-thinking default; Qwen XML tool calls; native 256K for agents (YaRN only for >256K). Multimodal works.

Quantization details

Tool: llm-compressor (compressed-tensors), using unsloth's exact config_groups + ignore.
Calibration: 512 samples from the Keural Nova v1.2 SFT mix, seq-len 2048.

Accuracy

Mixed FP8/FP4 keeps the most sensitive layers (linear-attn, gates, attention, final-layer experts) in higher precision, so this typically loses less than pure NVFP4 — the same design as unsloth's public checkpoint. Validate on Blackwell with scripts/nvfp4_verify_vllm.py against the bf16 base.

License & attribution

Apache-2.0, inheriting the base Qwen/Qwen3.6-35B-A3B license. Recipe after unsloth/Qwen3.6-35B-A3B-NVFP4. "Keural Nova" is a model by MKD.

Downloads last month: 157

Safetensors

Model size

22B params

Tensor type

BF16

F8_E4M3

Model tree for mkd-ai/Keural-Nova-v1.2-experimental-NVFP4-unsloth

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

mkd-hossain/Keural-Nova-v1.2-experimental

Quantized

(4)

this model