Text Generation
Transformers
Safetensors
qwen3_moe
neuralmagic
redhat
llmcompressor
quantized
FP8
conversational
compressed-tensors
Instructions to use RedHatAI/Qwen3-235B-A22B-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/Qwen3-235B-A22B-FP8-dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RedHatAI/Qwen3-235B-A22B-FP8-dynamic") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Qwen3-235B-A22B-FP8-dynamic") model = AutoModelForCausalLM.from_pretrained("RedHatAI/Qwen3-235B-A22B-FP8-dynamic") 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 Settings
- vLLM
How to use RedHatAI/Qwen3-235B-A22B-FP8-dynamic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RedHatAI/Qwen3-235B-A22B-FP8-dynamic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RedHatAI/Qwen3-235B-A22B-FP8-dynamic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RedHatAI/Qwen3-235B-A22B-FP8-dynamic
- SGLang
How to use RedHatAI/Qwen3-235B-A22B-FP8-dynamic 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 "RedHatAI/Qwen3-235B-A22B-FP8-dynamic" \ --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": "RedHatAI/Qwen3-235B-A22B-FP8-dynamic", "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 "RedHatAI/Qwen3-235B-A22B-FP8-dynamic" \ --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": "RedHatAI/Qwen3-235B-A22B-FP8-dynamic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RedHatAI/Qwen3-235B-A22B-FP8-dynamic with Docker Model Runner:
docker model run hf.co/RedHatAI/Qwen3-235B-A22B-FP8-dynamic
| { | |
| "architectures": [ | |
| "Qwen3MoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "decoder_sparse_step": 1, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 94, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_moe", | |
| "moe_intermediate_size": 1536, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 64, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 94, | |
| "num_key_value_heads": 4, | |
| "output_router_logits": false, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": null, | |
| "observer_kwargs": {}, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "float" | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "mse", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "float" | |
| } | |
| } | |
| }, | |
| "format": "float-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "model.layers.0.mlp.gate", | |
| "model.layers.1.mlp.gate", | |
| "model.layers.2.mlp.gate", | |
| "model.layers.3.mlp.gate", | |
| "model.layers.4.mlp.gate", | |
| "model.layers.5.mlp.gate", | |
| "model.layers.6.mlp.gate", | |
| "model.layers.7.mlp.gate", | |
| "model.layers.8.mlp.gate", | |
| "model.layers.9.mlp.gate", | |
| "model.layers.10.mlp.gate", | |
| "model.layers.11.mlp.gate", | |
| "model.layers.12.mlp.gate", | |
| "model.layers.13.mlp.gate", | |
| "model.layers.14.mlp.gate", | |
| "model.layers.15.mlp.gate", | |
| "model.layers.16.mlp.gate", | |
| "model.layers.17.mlp.gate", | |
| "model.layers.18.mlp.gate", | |
| "model.layers.19.mlp.gate", | |
| "model.layers.20.mlp.gate", | |
| "model.layers.21.mlp.gate", | |
| "model.layers.22.mlp.gate", | |
| "model.layers.23.mlp.gate", | |
| "model.layers.24.mlp.gate", | |
| "model.layers.25.mlp.gate", | |
| "model.layers.26.mlp.gate", | |
| "model.layers.27.mlp.gate", | |
| "model.layers.28.mlp.gate", | |
| "model.layers.29.mlp.gate", | |
| "model.layers.30.mlp.gate", | |
| "model.layers.31.mlp.gate", | |
| "model.layers.32.mlp.gate", | |
| "model.layers.33.mlp.gate", | |
| "model.layers.34.mlp.gate", | |
| "model.layers.35.mlp.gate", | |
| "model.layers.36.mlp.gate", | |
| "model.layers.37.mlp.gate", | |
| "model.layers.38.mlp.gate", | |
| "model.layers.39.mlp.gate", | |
| "model.layers.40.mlp.gate", | |
| "model.layers.41.mlp.gate", | |
| "model.layers.42.mlp.gate", | |
| "model.layers.43.mlp.gate", | |
| "model.layers.44.mlp.gate", | |
| "model.layers.45.mlp.gate", | |
| "model.layers.46.mlp.gate", | |
| "model.layers.47.mlp.gate", | |
| "model.layers.48.mlp.gate", | |
| "model.layers.49.mlp.gate", | |
| "model.layers.50.mlp.gate", | |
| "model.layers.51.mlp.gate", | |
| "model.layers.52.mlp.gate", | |
| "model.layers.53.mlp.gate", | |
| "model.layers.54.mlp.gate", | |
| "model.layers.55.mlp.gate", | |
| "model.layers.56.mlp.gate", | |
| "model.layers.57.mlp.gate", | |
| "model.layers.58.mlp.gate", | |
| "model.layers.59.mlp.gate", | |
| "model.layers.60.mlp.gate", | |
| "model.layers.61.mlp.gate", | |
| "model.layers.62.mlp.gate", | |
| "model.layers.63.mlp.gate", | |
| "model.layers.64.mlp.gate", | |
| "model.layers.65.mlp.gate", | |
| "model.layers.66.mlp.gate", | |
| "model.layers.67.mlp.gate", | |
| "model.layers.68.mlp.gate", | |
| "model.layers.69.mlp.gate", | |
| "model.layers.70.mlp.gate", | |
| "model.layers.71.mlp.gate", | |
| "model.layers.72.mlp.gate", | |
| "model.layers.73.mlp.gate", | |
| "model.layers.74.mlp.gate", | |
| "model.layers.75.mlp.gate", | |
| "model.layers.76.mlp.gate", | |
| "model.layers.77.mlp.gate", | |
| "model.layers.78.mlp.gate", | |
| "model.layers.79.mlp.gate", | |
| "model.layers.80.mlp.gate", | |
| "model.layers.81.mlp.gate", | |
| "model.layers.82.mlp.gate", | |
| "model.layers.83.mlp.gate", | |
| "model.layers.84.mlp.gate", | |
| "model.layers.85.mlp.gate", | |
| "model.layers.86.mlp.gate", | |
| "model.layers.87.mlp.gate", | |
| "model.layers.88.mlp.gate", | |
| "model.layers.89.mlp.gate", | |
| "model.layers.90.mlp.gate", | |
| "model.layers.91.mlp.gate", | |
| "model.layers.92.mlp.gate", | |
| "model.layers.93.mlp.gate", | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } |