Instructions to use 0xSero/Qwen3.5-264B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/Qwen3.5-264B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="0xSero/Qwen3.5-264B-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xSero/Qwen3.5-264B-FP8")
model = AutoModelForCausalLM.from_pretrained("0xSero/Qwen3.5-264B-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 0xSero/Qwen3.5-264B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/Qwen3.5-264B-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": "0xSero/Qwen3.5-264B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/Qwen3.5-264B-FP8

SGLang

How to use 0xSero/Qwen3.5-264B-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 "0xSero/Qwen3.5-264B-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": "0xSero/Qwen3.5-264B-FP8",
		"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 "0xSero/Qwen3.5-264B-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": "0xSero/Qwen3.5-264B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xSero/Qwen3.5-264B-FP8 with Docker Model Runner:
```
docker model run hf.co/0xSero/Qwen3.5-264B-FP8
```

Support this work → · X · GitHub · REAP paper · Cerebras REAP

Qwen3.5-264B-FP8

FP8 quantization of 0xSero/Qwen3.5-264B.

At a glance


Base model	0xSero/Qwen3.5-264B
Format	FP8
Total params	264B
Active / token	—
Experts / layer	336
Layers	60
Hidden size	4096
Context	262,144
On-disk size	272 GB

Which variant should I pick?

Variant	Format	Link
`Qwen3.5-264B`	BF16	link
`Qwen3.5-264B-FP8` (this)	FP8	link
`Qwen3.5-264B-W4A16`	W4A16	link
`Qwen3.5-28B`	BF16	link
`Qwen3.5-35B-EXL3-4bpw`	EXL3-4bpw	link
`Qwen3.5-76B`	BF16	link
`Qwen3.5-76B-GGUF`	GGUF	link
`Qwen3.5-88B`	BF16	link
`Qwen3.5-99B`	BF16	link
`Qwen3.5-99B-GGUF`	GGUF	link

Repository: 0xSero/Qwen3.5-264B-FP8
Base model: 0xSero/Qwen3.5-264B (BF16)
Original model: Qwen/Qwen3.5-397B-A17B
Artifact kind: pruned + quantized
Quantization: FP8 W8A8 (float8_e4m3fn), per-tensor dynamic
Compression ratio: ~48% (from BF16 REAP checkpoint)

Details

Maintainer: 0xSero
Organization: Sybil Solutions
Project: REAP PR17

Model Description

FP8 quantized version of Qwen3.5-264B-REAP, a REAP-pruned Qwen3.5-397B-A17B with 176 of 512 experts removed per MoE layer, retaining 336 experts per layer, for an estimated 264B total parameters.

Quantization Details

Format: float8_e4m3fn (FP8 E4M3, 4-bit exponent, 3-bit mantissa)
Scheme: Per-tensor symmetric dynamic quantization
Targets: All Linear layer weights (q/k/v/o projections, gate/up/down projections, MoE expert and shared expert projections)
Ignored: lm_head, layer norms, embeddings, biases
Serialization: compressed-tensors format (native vLLM/SGLang support)
Size: ~253GB on disk (down from ~491GB BF16)

Hardware Compatibility

NVIDIA Ada Lovelace (SM89): via Marlin FP8 kernel
NVIDIA Hopper (SM90): native FP8 tensor core support
NVIDIA Blackwell (SM100/SM120): native FP8 tensor core support

Vision Encoder

Vision encoder weights from Qwen/Qwen3.5-397B-A17B are included (333 tensors, ~910MB BF16). The VL encoder is not quantized -- it remains in original BF16 precision.

Usage

vLLM

vllm serve 0xSero/Qwen3.5-264B-FP8 \
  --tensor-parallel-size 4 \
  --quantization fp8 \
  --kv-cache-dtype auto \
  --trust-remote-code

Note: Use --kv-cache-dtype auto (not fp8_e4m3) on Blackwell (SM120) GPUs to avoid garbled output.

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "0xSero/Qwen3.5-264B-FP8",
    trust_remote_code=True,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("0xSero/Qwen3.5-264B-FP8", trust_remote_code=True)

Provenance

Source checkpoint: 0xSero/Qwen3.5-264B (BF16, REAP-pruned)
Quantization method: Per-tensor dynamic FP8 cast with compressed-tensors config
Quantization compute: CPU-only (no calibration data required for weight-only FP8)

License & citation

License inherited from the base model.

@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}

Model tree for 0xSero/Qwen3.5-264B-FP8

Base model

Qwen/Qwen3.5-397B-A17B

Finetuned

0xSero/Qwen3.5-264B

Quantized

(1)

this model

Datasets used to train 0xSero/Qwen3.5-264B-FP8

Collection including 0xSero/Qwen3.5-264B-FP8

Qwen — REAP

Collection

REAP-pruned & quantized Qwen3.5 / 3.6 / Coder variants. • 15 items • Updated 3 days ago

Paper for 0xSero/Qwen3.5-264B-FP8

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 20

0xSero
/

Qwen3.5-264B-FP8

Qwen3.5-264B-FP8

At a glance

Which variant should I pick?

Details

Model Description

Quantization Details

Hardware Compatibility

Vision Encoder

Usage

vLLM

Transformers

Provenance

License & citation

Sponsors

Model tree for 0xSero/Qwen3.5-264B-FP8

Datasets used to train 0xSero/Qwen3.5-264B-FP8

Collection including 0xSero/Qwen3.5-264B-FP8

Qwen — REAP

Paper for 0xSero/Qwen3.5-264B-FP8

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression