Instructions to use tiny-random/qwen3.8-moe-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/qwen3.8-moe-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/qwen3.8-moe-fp8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiny-random/qwen3.8-moe-fp8")
model = AutoModelForCausalLM.from_pretrained("tiny-random/qwen3.8-moe-fp8", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/qwen3.8-moe-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/qwen3.8-moe-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": "tiny-random/qwen3.8-moe-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/qwen3.8-moe-fp8

SGLang

How to use tiny-random/qwen3.8-moe-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 "tiny-random/qwen3.8-moe-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": "tiny-random/qwen3.8-moe-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 "tiny-random/qwen3.8-moe-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": "tiny-random/qwen3.8-moe-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/qwen3.8-moe-fp8 with Docker Model Runner:
```
docker model run hf.co/tiny-random/qwen3.8-moe-fp8
```

qwen3.8-moe-fp8 / config.json

yujiepan

Upload folder using huggingface_hub

5eea276 verified 6 days ago

Raw History Blame Contribute Delete

6.03 kB

{
  "architectures": [
    "Qwen3_5MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_output_gate": true,
  "bos_token_id": 248044,
  "dtype": "bfloat16",
  "eos_token_id": 248044,
  "full_attention_interval": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 32,
  "initializer_range": 0.02,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 2,
  "linear_num_value_heads": 16,
  "linear_value_head_dim": 128,
  "mamba_ssm_dtype": "float32",
  "max_position_embeddings": 262144,
  "model_type": "qwen3_5_moe_text",
  "moe_intermediate_size": 128,
  "mtp_num_hidden_layers": 1,
  "mtp_use_dedicated_embeddings": false,
  "num_attention_heads": 32,
  "num_experts": 32,
  "num_experts_per_tok": 10,
  "num_hidden_layers": 8,
  "num_key_value_heads": 2,
  "output_gate_type": "swish",
  "output_router_logits": false,
  "pad_token_id": null,
  "partial_rotary_factor": 0.25,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "partial_rotary_factor": 0.25,
    "rope_theta": 10000000,
    "rope_type": "default"
  },
  "router_aux_loss_coef": 0.001,
  "shared_expert_intermediate_size": 128,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 248320,
  "quantization_config": {
    "quant_method": "fp8",
    "activation_scheme": "dynamic",
    "weight_per_tensor": false,
    "act_per_tensor": false,
    "weight_block_size": [
      32,
      32
    ],
    "modules_to_not_convert": [
      "lm_head",
      "model.embed_tokens",
      "model.layers.0.linear_attn.conv1d",
      "model.layers.0.linear_attn.in_proj_a",
      "model.layers.0.linear_attn.in_proj_b",
      "model.layers.0.linear_attn.in_proj_qkv",
      "model.layers.0.linear_attn.in_proj_z",
      "model.layers.0.linear_attn.out_proj",
      "model.layers.0.mlp.gate",
      "model.layers.0.mlp.shared_expert.down_proj",
      "model.layers.0.mlp.shared_expert.gate_proj",
      "model.layers.0.mlp.shared_expert.up_proj",
      "model.layers.0.mlp.shared_expert_gate",
      "model.layers.1.linear_attn.conv1d",
      "model.layers.1.linear_attn.in_proj_a",
      "model.layers.1.linear_attn.in_proj_b",
      "model.layers.1.linear_attn.in_proj_qkv",
      "model.layers.1.linear_attn.in_proj_z",
      "model.layers.1.linear_attn.out_proj",
      "model.layers.1.mlp.gate",
      "model.layers.1.mlp.shared_expert.down_proj",
      "model.layers.1.mlp.shared_expert.gate_proj",
      "model.layers.1.mlp.shared_expert.up_proj",
      "model.layers.1.mlp.shared_expert_gate",
      "model.layers.2.linear_attn.conv1d",
      "model.layers.2.linear_attn.in_proj_a",
      "model.layers.2.linear_attn.in_proj_b",
      "model.layers.2.linear_attn.in_proj_qkv",
      "model.layers.2.linear_attn.in_proj_z",
      "model.layers.2.linear_attn.out_proj",
      "model.layers.2.mlp.gate",
      "model.layers.2.mlp.shared_expert.down_proj",
      "model.layers.2.mlp.shared_expert.gate_proj",
      "model.layers.2.mlp.shared_expert.up_proj",
      "model.layers.2.mlp.shared_expert_gate",
      "model.layers.3.mlp.gate",
      "model.layers.3.mlp.shared_expert.down_proj",
      "model.layers.3.mlp.shared_expert.gate_proj",
      "model.layers.3.mlp.shared_expert.up_proj",
      "model.layers.3.mlp.shared_expert_gate",
      "model.layers.3.self_attn.k_proj",
      "model.layers.3.self_attn.o_proj",
      "model.layers.3.self_attn.q_proj",
      "model.layers.3.self_attn.v_proj",
      "model.layers.4.linear_attn.conv1d",
      "model.layers.4.linear_attn.in_proj_a",
      "model.layers.4.linear_attn.in_proj_b",
      "model.layers.4.linear_attn.in_proj_qkv",
      "model.layers.4.linear_attn.in_proj_z",
      "model.layers.4.linear_attn.out_proj",
      "model.layers.4.mlp.gate",
      "model.layers.4.mlp.shared_expert.down_proj",
      "model.layers.4.mlp.shared_expert.gate_proj",
      "model.layers.4.mlp.shared_expert.up_proj",
      "model.layers.4.mlp.shared_expert_gate",
      "model.layers.5.linear_attn.conv1d",
      "model.layers.5.linear_attn.in_proj_a",
      "model.layers.5.linear_attn.in_proj_b",
      "model.layers.5.linear_attn.in_proj_qkv",
      "model.layers.5.linear_attn.in_proj_z",
      "model.layers.5.linear_attn.out_proj",
      "model.layers.5.mlp.gate",
      "model.layers.5.mlp.shared_expert.down_proj",
      "model.layers.5.mlp.shared_expert.gate_proj",
      "model.layers.5.mlp.shared_expert.up_proj",
      "model.layers.5.mlp.shared_expert_gate",
      "model.layers.6.linear_attn.conv1d",
      "model.layers.6.linear_attn.in_proj_a",
      "model.layers.6.linear_attn.in_proj_b",
      "model.layers.6.linear_attn.in_proj_qkv",
      "model.layers.6.linear_attn.in_proj_z",
      "model.layers.6.linear_attn.out_proj",
      "model.layers.6.mlp.gate",
      "model.layers.6.mlp.shared_expert.down_proj",
      "model.layers.6.mlp.shared_expert.gate_proj",
      "model.layers.6.mlp.shared_expert.up_proj",
      "model.layers.6.mlp.shared_expert_gate",
      "model.layers.7.mlp.gate",
      "model.layers.7.mlp.shared_expert.down_proj",
      "model.layers.7.mlp.shared_expert.gate_proj",
      "model.layers.7.mlp.shared_expert.up_proj",
      "model.layers.7.mlp.shared_expert_gate",
      "model.layers.7.self_attn.k_proj",
      "model.layers.7.self_attn.o_proj",
      "model.layers.7.self_attn.q_proj",
      "model.layers.7.self_attn.v_proj",
      "mtp.fc",
      "mtp.layers.0.mlp.gate",
      "mtp.layers.0.mlp.shared_expert.down_proj",
      "mtp.layers.0.mlp.shared_expert.gate_proj",
      "mtp.layers.0.mlp.shared_expert.up_proj",
      "mtp.layers.0.mlp.shared_expert_gate",
      "mtp.layers.0.self_attn.k_proj",
      "mtp.layers.0.self_attn.o_proj",
      "mtp.layers.0.self_attn.q_proj",
      "mtp.layers.0.self_attn.v_proj"
    ]
  }
}

	{
	"architectures": [
	"Qwen3_5MoeForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": 248044,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 32,
	"initializer_range": 0.02,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 2,
	"linear_num_value_heads": 16,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"model_type": "qwen3_5_moe_text",
	"moe_intermediate_size": 128,
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 32,
	"num_experts": 32,
	"num_experts_per_tok": 10,
	"num_hidden_layers": 8,
	"num_key_value_heads": 2,
	"output_gate_type": "swish",
	"output_router_logits": false,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"router_aux_loss_coef": 0.001,
	"shared_expert_intermediate_size": 128,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.3",
	"use_cache": true,
	"vocab_size": 248320,
	"quantization_config": {
	"quant_method": "fp8",
	"activation_scheme": "dynamic",
	"weight_per_tensor": false,
	"act_per_tensor": false,
	"weight_block_size": [
	32,
	32
	],
	"modules_to_not_convert": [
	"lm_head",
	"model.embed_tokens",
	"model.layers.0.linear_attn.conv1d",
	"model.layers.0.linear_attn.in_proj_a",
	"model.layers.0.linear_attn.in_proj_b",
	"model.layers.0.linear_attn.in_proj_qkv",
	"model.layers.0.linear_attn.in_proj_z",
	"model.layers.0.linear_attn.out_proj",
	"model.layers.0.mlp.gate",
	"model.layers.0.mlp.shared_expert.down_proj",
	"model.layers.0.mlp.shared_expert.gate_proj",
	"model.layers.0.mlp.shared_expert.up_proj",
	"model.layers.0.mlp.shared_expert_gate",
	"model.layers.1.linear_attn.conv1d",
	"model.layers.1.linear_attn.in_proj_a",
	"model.layers.1.linear_attn.in_proj_b",
	"model.layers.1.linear_attn.in_proj_qkv",
	"model.layers.1.linear_attn.in_proj_z",
	"model.layers.1.linear_attn.out_proj",
	"model.layers.1.mlp.gate",
	"model.layers.1.mlp.shared_expert.down_proj",
	"model.layers.1.mlp.shared_expert.gate_proj",
	"model.layers.1.mlp.shared_expert.up_proj",
	"model.layers.1.mlp.shared_expert_gate",
	"model.layers.2.linear_attn.conv1d",
	"model.layers.2.linear_attn.in_proj_a",
	"model.layers.2.linear_attn.in_proj_b",
	"model.layers.2.linear_attn.in_proj_qkv",
	"model.layers.2.linear_attn.in_proj_z",
	"model.layers.2.linear_attn.out_proj",
	"model.layers.2.mlp.gate",
	"model.layers.2.mlp.shared_expert.down_proj",
	"model.layers.2.mlp.shared_expert.gate_proj",
	"model.layers.2.mlp.shared_expert.up_proj",
	"model.layers.2.mlp.shared_expert_gate",
	"model.layers.3.mlp.gate",
	"model.layers.3.mlp.shared_expert.down_proj",
	"model.layers.3.mlp.shared_expert.gate_proj",
	"model.layers.3.mlp.shared_expert.up_proj",
	"model.layers.3.mlp.shared_expert_gate",
	"model.layers.3.self_attn.k_proj",
	"model.layers.3.self_attn.o_proj",
	"model.layers.3.self_attn.q_proj",
	"model.layers.3.self_attn.v_proj",
	"model.layers.4.linear_attn.conv1d",
	"model.layers.4.linear_attn.in_proj_a",
	"model.layers.4.linear_attn.in_proj_b",
	"model.layers.4.linear_attn.in_proj_qkv",
	"model.layers.4.linear_attn.in_proj_z",
	"model.layers.4.linear_attn.out_proj",
	"model.layers.4.mlp.gate",
	"model.layers.4.mlp.shared_expert.down_proj",
	"model.layers.4.mlp.shared_expert.gate_proj",
	"model.layers.4.mlp.shared_expert.up_proj",
	"model.layers.4.mlp.shared_expert_gate",
	"model.layers.5.linear_attn.conv1d",
	"model.layers.5.linear_attn.in_proj_a",
	"model.layers.5.linear_attn.in_proj_b",
	"model.layers.5.linear_attn.in_proj_qkv",
	"model.layers.5.linear_attn.in_proj_z",
	"model.layers.5.linear_attn.out_proj",
	"model.layers.5.mlp.gate",
	"model.layers.5.mlp.shared_expert.down_proj",
	"model.layers.5.mlp.shared_expert.gate_proj",
	"model.layers.5.mlp.shared_expert.up_proj",
	"model.layers.5.mlp.shared_expert_gate",
	"model.layers.6.linear_attn.conv1d",
	"model.layers.6.linear_attn.in_proj_a",
	"model.layers.6.linear_attn.in_proj_b",
	"model.layers.6.linear_attn.in_proj_qkv",
	"model.layers.6.linear_attn.in_proj_z",
	"model.layers.6.linear_attn.out_proj",
	"model.layers.6.mlp.gate",
	"model.layers.6.mlp.shared_expert.down_proj",
	"model.layers.6.mlp.shared_expert.gate_proj",
	"model.layers.6.mlp.shared_expert.up_proj",
	"model.layers.6.mlp.shared_expert_gate",
	"model.layers.7.mlp.gate",
	"model.layers.7.mlp.shared_expert.down_proj",
	"model.layers.7.mlp.shared_expert.gate_proj",
	"model.layers.7.mlp.shared_expert.up_proj",
	"model.layers.7.mlp.shared_expert_gate",
	"model.layers.7.self_attn.k_proj",
	"model.layers.7.self_attn.o_proj",
	"model.layers.7.self_attn.q_proj",
	"model.layers.7.self_attn.v_proj",
	"mtp.fc",
	"mtp.layers.0.mlp.gate",
	"mtp.layers.0.mlp.shared_expert.down_proj",
	"mtp.layers.0.mlp.shared_expert.gate_proj",
	"mtp.layers.0.mlp.shared_expert.up_proj",
	"mtp.layers.0.mlp.shared_expert_gate",
	"mtp.layers.0.self_attn.k_proj",
	"mtp.layers.0.self_attn.o_proj",
	"mtp.layers.0.self_attn.q_proj",
	"mtp.layers.0.self_attn.v_proj"
	]
	}
	}