Instructions to use nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8")
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("nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8")
model = AutoModelForMultimodalLM.from_pretrained("nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8", 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 nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8

SGLang

How to use nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8 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 "nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8" \
    --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": "nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8" \
        --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": "nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8 with Docker Model Runner:
```
docker model run hf.co/nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8
```

Qwen3.5-122B-A10B-heretic-v2-FP8

FP8 block-wise quantization of coder3101/Qwen3.5-122B-A10B-heretic-v2 (abliterated via Heretic).

Quantization format matches Qwen/Qwen3.5-122B-A10B-FP8 exactly (same tensor names, scale format, skip list).

Quantization Details

Parameter	Value
Method	FP8 E4M3 block-wise
Block size	128x128
Scale dtype	BF16
Scale naming	`weight_scale_inv`
Activation scheme	Dynamic
Original size	~227 GB (BF16)
Quantized size	~117 GB

What's quantized

All linear projections in attention (q/k/v/o_proj), GatedDeltaNet (in_proj_qkv, in_proj_z, out_proj), and MLP experts (gate/up/down_proj for all experts + shared expert).

What's kept in BF16

Embeddings, lm_head, norms, MoE router gates, GDN precision-sensitive params (conv1d, in_proj_a, in_proj_b), vision tower.

Usage with SGLang (2+ GPUs)

python -m sglang.launch_server \
    --model-path nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8 \
    --tp 2 \
    --port 30000 --host 0.0.0.0 \
    --mem-fraction-static 0.85 \
    --context-length 32768 \
    --attention-backend triton \
    --reasoning-parser qwen3 \
    --tool-call-parser qwen3_coder \
    --mamba-scheduler-strategy extra_buffer \
    --trust-remote-code

Usage with vLLM

from vllm import LLM
model = LLM("nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8", tensor_parallel_size=2, trust_remote_code=True)

Notes

No MTP: Heretic abliteration strips MTP weights. Do not use --speculative-algo NEXTN (accept rate ~0.25). Restoring MTP by copying the head from the original Qwen model and fine-tuning against heretic hidden states is a potential future improvement.
Thinking model: Supports <think> reasoning. Use "chat_template_kwargs": {"enable_thinking": false} to disable.
VRAM: ~117 GB model weights. Requires 2x H100 80GB, 1x H200 141GB (tight), or 2x RTX PRO 6000 96GB.
Validated against official Qwen/Qwen3.5-122B-A10B-FP8: 0 missing scale tensors, 0 unexpected tensors, matching quantization config.

Credits

Base model: Qwen/Qwen3.5-122B-A10B by Qwen Team
Abliteration: coder3101/Qwen3.5-122B-A10B-heretic-v2 using Heretic
FP8 quantization: nivvis

Downloads last month: 424

Safetensors

Model size

122B params

Tensor type

BF16

F8_E4M3

Collection including nivvis/Qwen3.5-122B-A10B-heretic-v2-FP8

Qwen3.5 Heretic Quants

Collection

4 items • Updated Mar 29