Instructions to use unsloth/GLM-4.7-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/GLM-4.7-Flash-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/GLM-4.7-Flash-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/GLM-4.7-Flash-NVFP4")
model = AutoModelForCausalLM.from_pretrained("unsloth/GLM-4.7-Flash-NVFP4", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/GLM-4.7-Flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/GLM-4.7-Flash-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/GLM-4.7-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/GLM-4.7-Flash-NVFP4

SGLang

How to use unsloth/GLM-4.7-Flash-NVFP4 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 "unsloth/GLM-4.7-Flash-NVFP4" \
    --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": "unsloth/GLM-4.7-Flash-NVFP4",
		"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 "unsloth/GLM-4.7-Flash-NVFP4" \
        --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": "unsloth/GLM-4.7-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use unsloth/GLM-4.7-Flash-NVFP4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/GLM-4.7-Flash-NVFP4 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/GLM-4.7-Flash-NVFP4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/GLM-4.7-Flash-NVFP4 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/GLM-4.7-Flash-NVFP4",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/GLM-4.7-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/unsloth/GLM-4.7-Flash-NVFP4
```

GLM-4.7-Flash-NVFP4 / config.json

danielhanchen

Add files using upload-large-folder tool

e3a51ea verified 18 days ago

Raw

History Blame Contribute Delete

6.38 kB

	{
	"architectures": [
	"Glm4MoeLiteForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 0,
	"dtype": "bfloat16",
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"first_k_dense_replace": 1,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 10240,
	"kv_lora_rank": 512,
	"max_position_embeddings": 202752,
	"mlp_layer_types": [
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "glm4_moe_lite",
	"moe_intermediate_size": 1536,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 20,
	"num_experts_per_tok": 4,
	"num_hidden_layers": 47,
	"num_key_value_heads": 20,
	"num_nextn_predict_layers": 1,
	"pad_token_id": 154821,
	"partial_rotary_factor": 1.0,
	"pretraining_tp": 1,
	"q_lora_rank": 768,
	"qk_head_dim": 256,
	"qk_nope_head_dim": 192,
	"qk_rope_head_dim": 64,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "float-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": null,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "token",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"re:.*self_attn\\.(q_a_proj\|q_b_proj\|kv_a_proj_with_mqa\|kv_b_proj\|o_proj)$",
	"re:.*lm_head",
	"re:.*layers\\.(1\|39\|46)\\.mlp\\.experts\\.\\d+\\.(gate\|up\|down)_proj$",
	"re:.*layers\\.(1\|39\|46)\\.mlp\\.shared_experts\\.(gate\|up\|down)_proj$",
	"re:.*layers\\.(1\|39\|46)\\.mlp\\.(gate\|up\|down)_proj$"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "channel",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	},
	"group_1": {
	"format": "nvfp4-pack-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": "local",
	"group_size": 16,
	"num_bits": 4,
	"observer": "static_minmax",
	"observer_kwargs": {},
	"scale_dtype": "torch.float8_e4m3fn",
	"strategy": "tensor_group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"re:.*mlp\\.experts\\.\\d+\\.(gate\|up\|down)_proj$",
	"re:.*mlp\\.shared_experts\\.(gate\|up\|down)_proj$",
	"re:.*mlp\\.(gate\|up\|down)_proj$"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 16,
	"num_bits": 4,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": "torch.float8_e4m3fn",
	"strategy": "tensor_group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "mixed-precision",
	"global_compression_ratio": null,
	"ignore": [
	"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",
	"re:^model.layers.47..*"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.17.2.a20260707"
	},
	"rms_norm_eps": 1e-05,
	"rope_interleave": true,
	"rope_parameters": {
	"partial_rotary_factor": 1.0,
	"rope_theta": 1000000,
	"rope_type": "default"
	},
	"routed_scaling_factor": 1.8,
	"scoring_func": "sigmoid",
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"transformers_version": "5.13.0",
	"unsloth_fixed": true,
	"use_cache": true,
	"v_head_dim": 256,
	"vocab_size": 154880
	}