Instructions to use Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM",
		"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/Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM

SGLang

How to use Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM 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 "Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM" \
    --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": "Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM",
		"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 "Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM" \
        --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": "Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM with Docker Model Runner:
```
docker model run hf.co/Xingyu-Zheng/Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM
```

Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM / config.json

Xingyu-Zheng

Upload folder using huggingface_hub

13d0bf9 verified 5 months ago

Raw

History Blame Contribute Delete

4.44 kB

	{
	"architectures": [
	"Qwen3_5ForConditionalGeneration"
	],
	"dtype": "bfloat16",
	"eos_token_id": 248046,
	"image_token_id": 248056,
	"model_name": "unsloth/Qwen3.5-9B",
	"model_type": "qwen3_5",
	"pad_token_id": 248055,
	"quantization_config": {
	"bits": 4,
	"checkpoint_format": "gptq",
	"desc_act": false,
	"format": "gptq",
	"group_size": 128,
	"lm_head": false,
	"meta": {
	"act_group_aware": true,
	"auto_forward_data_parallel": true,
	"damp_auto_increment": 0.01,
	"damp_percent": 0.05,
	"dense_vram_strategy": "exclusive",
	"dense_vram_strategy_devices": null,
	"fallback": {
	"smooth": null,
	"strategy": "rtn",
	"threshold": "0.5%"
	},
	"foem": {
	"alpha": 0,
	"beta": 0.2,
	"device": "auto"
	},
	"gc_mode": "interval",
	"gptaq": null,
	"hessian": {
	"chunk_bytes": null,
	"chunk_size": null,
	"staging_dtype": "float32"
	},
	"mock_quantization": false,
	"moe_vram_strategy": "exclusive",
	"moe_vram_strategy_devices": null,
	"mse": 0.0,
	"offload_to_disk": true,
	"offload_to_disk_path": "./gptqmodel_offload/tkjfqxnv-hfdznbuo/",
	"pack_impl": "cpu",
	"quantizer": [
	"gptqmodel:6.1.0-dev"
	],
	"static_groups": false,
	"true_sequential": true,
	"uri": "https://github.com/modelcloud/gptqmodel",
	"wait_for_submodule_finalizers": false
	},
	"method": "gptq",
	"pack_dtype": "int32",
	"quant_method": "gptq",
	"sym": true
	},
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"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": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"model_type": "qwen3_5_text",
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 16,
	"num_hidden_layers": 32,
	"num_key_value_heads": 4,
	"pad_token_id": 248055,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"use_cache": true,
	"vocab_size": 248320
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.5.0.dev0",
	"unsloth_fixed": true,
	"unsloth_version": "2026.4.5",
	"use_cache": false,
	"video_token_id": 248057,
	"vision_config": {
	"deepstack_visual_indexes": [],
	"depth": 27,
	"dtype": "bfloat16",
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4304,
	"model_type": "qwen3_5",
	"num_heads": 16,
	"num_position_embeddings": 2304,
	"out_hidden_size": 4096,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 248054,
	"vision_start_token_id": 248053
	}