How to use from
SGLangUse 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 "majentik/Qwen3.6-35B-A3B-FP8" \
--host 0.0.0.0 \
--port 30000# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "majentik/Qwen3.6-35B-A3B-FP8",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Qwen3.6-35B-A3B-FP8
Summary
Reference wrapper around Qwen/Qwen3.6-35B-A3B-FP8 — the official FP8 release. This repository carries no weights; it exists only to anchor the FP8 variant inside the majentik/* family navigation.
Why this variant
Pick this for Hopper / Ada / Blackwell GPUs where FP8 is natively supported and you want the closest-to-bf16 fidelity with ~50% memory savings. For additional compression pick one of the 4-bit variants below.
Hardware compatibility
| Device | VRAM | Recommendation |
|---|---|---|
| H100 / H200 | 80–141 GB | native |
| RTX 4090 | 24 GB | does not fit full precision — use 4-bit |
| RTX 5090 | 32 GB | native |
Reproduce
# No re-quantization needed — use the upstream weights directly.
huggingface-cli download Qwen/Qwen3.6-35B-A3B-FP8
Evaluation
Benchmarks pending — populated after the eval-harness workstream lands.
Family
- bf16 — Qwen/Qwen3.6-35B-A3B
- FP8 (this) — Qwen/Qwen3.6-35B-A3B-FP8
- RotorQuant family — majentik/Qwen3.6-35B-A3B-RotorQuant
- TurboQuant family — majentik/Qwen3.6-35B-A3B-TurboQuant
Provenance
Card-only. No weights stored.
License
Released under apache-2.0. Upstream license of the base model applies.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "majentik/Qwen3.6-35B-A3B-FP8" \ --host 0.0.0.0 \ --port 30000# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "majentik/Qwen3.6-35B-A3B-FP8", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'