Instructions to use RedHatAI/GLM-5.2-NVFP4-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/GLM-5.2-NVFP4-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/GLM-5.2-NVFP4-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/GLM-5.2-NVFP4-FP8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/GLM-5.2-NVFP4-FP8")
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/GLM-5.2-NVFP4-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/GLM-5.2-NVFP4-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": "RedHatAI/GLM-5.2-NVFP4-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/GLM-5.2-NVFP4-FP8

SGLang

How to use RedHatAI/GLM-5.2-NVFP4-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 "RedHatAI/GLM-5.2-NVFP4-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": "RedHatAI/GLM-5.2-NVFP4-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 "RedHatAI/GLM-5.2-NVFP4-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": "RedHatAI/GLM-5.2-NVFP4-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/GLM-5.2-NVFP4-FP8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/GLM-5.2-NVFP4-FP8
```

GLM-5.2-NVFP4-FP8 / config.json

bdellabe

Add mtp regex to ignore list

6a0ebef verified 2 days ago

Raw

History Blame

9.87 kB

	{
	"architectures": [
	"GlmMoeDsaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 0,
	"dtype": "bfloat16",
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"ep_size": 1,
	"first_k_dense_replace": 3,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 6144,
	"index_head_dim": 128,
	"index_n_heads": 32,
	"index_share_for_mtp_iteration": true,
	"index_skip_topk_offset": 3,
	"index_topk": 2048,
	"index_topk_freq": 4,
	"index_topk_pattern": null,
	"indexer_rope_interleave": true,
	"indexer_types": [
	"full",
	"full",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared"
	],
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"kv_lora_rank": 512,
	"max_position_embeddings": 1048576,
	"mlp_bias": false,
	"mlp_layer_types": [
	"dense",
	"dense",
	"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",
	"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": "glm_moe_dsa",
	"moe_intermediate_size": 2048,
	"moe_layer_freq": 1,
	"n_group": 1,
	"n_routed_experts": 256,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 78,
	"num_key_value_heads": 64,
	"num_nextn_predict_layers": 1,
	"pad_token_id": 154820,
	"pretraining_tp": 1,
	"q_lora_rank": 2048,
	"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": 128,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"re:.self_attn\\.."
	],
	"weights": {
	"actorder": null,
	"block_structure": [
	128,
	128
	],
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "block",
	"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\\.."
	],
	"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": [
	"re:.mtp.",
	"model.layers.0.self_attn.indexer.weights_proj",
	"model.layers.1.self_attn.indexer.weights_proj",
	"model.layers.2.self_attn.indexer.weights_proj",
	"model.layers.3.mlp.gate",
	"model.layers.4.mlp.gate",
	"model.layers.5.mlp.gate",
	"model.layers.6.self_attn.indexer.weights_proj",
	"model.layers.6.mlp.gate",
	"model.layers.7.mlp.gate",
	"model.layers.8.mlp.gate",
	"model.layers.9.mlp.gate",
	"model.layers.10.self_attn.indexer.weights_proj",
	"model.layers.10.mlp.gate",
	"model.layers.11.mlp.gate",
	"model.layers.12.mlp.gate",
	"model.layers.13.mlp.gate",
	"model.layers.14.self_attn.indexer.weights_proj",
	"model.layers.14.mlp.gate",
	"model.layers.15.mlp.gate",
	"model.layers.16.mlp.gate",
	"model.layers.17.mlp.gate",
	"model.layers.18.self_attn.indexer.weights_proj",
	"model.layers.18.mlp.gate",
	"model.layers.19.mlp.gate",
	"model.layers.20.mlp.gate",
	"model.layers.21.mlp.gate",
	"model.layers.22.self_attn.indexer.weights_proj",
	"model.layers.22.mlp.gate",
	"model.layers.23.mlp.gate",
	"model.layers.24.mlp.gate",
	"model.layers.25.mlp.gate",
	"model.layers.26.self_attn.indexer.weights_proj",
	"model.layers.26.mlp.gate",
	"model.layers.27.mlp.gate",
	"model.layers.28.mlp.gate",
	"model.layers.29.mlp.gate",
	"model.layers.30.self_attn.indexer.weights_proj",
	"model.layers.30.mlp.gate",
	"model.layers.31.mlp.gate",
	"model.layers.32.mlp.gate",
	"model.layers.33.mlp.gate",
	"model.layers.34.self_attn.indexer.weights_proj",
	"model.layers.34.mlp.gate",
	"model.layers.35.mlp.gate",
	"model.layers.36.mlp.gate",
	"model.layers.37.mlp.gate",
	"model.layers.38.self_attn.indexer.weights_proj",
	"model.layers.38.mlp.gate",
	"model.layers.39.mlp.gate",
	"model.layers.40.mlp.gate",
	"model.layers.41.mlp.gate",
	"model.layers.42.self_attn.indexer.weights_proj",
	"model.layers.42.mlp.gate",
	"model.layers.43.mlp.gate",
	"model.layers.44.mlp.gate",
	"model.layers.45.mlp.gate",
	"model.layers.46.self_attn.indexer.weights_proj",
	"model.layers.46.mlp.gate",
	"model.layers.47.mlp.gate",
	"model.layers.48.mlp.gate",
	"model.layers.49.mlp.gate",
	"model.layers.50.self_attn.indexer.weights_proj",
	"model.layers.50.mlp.gate",
	"model.layers.51.mlp.gate",
	"model.layers.52.mlp.gate",
	"model.layers.53.mlp.gate",
	"model.layers.54.self_attn.indexer.weights_proj",
	"model.layers.54.mlp.gate",
	"model.layers.55.mlp.gate",
	"model.layers.56.mlp.gate",
	"model.layers.57.mlp.gate",
	"model.layers.58.self_attn.indexer.weights_proj",
	"model.layers.58.mlp.gate",
	"model.layers.59.mlp.gate",
	"model.layers.60.mlp.gate",
	"model.layers.61.mlp.gate",
	"model.layers.62.self_attn.indexer.weights_proj",
	"model.layers.62.mlp.gate",
	"model.layers.63.mlp.gate",
	"model.layers.64.mlp.gate",
	"model.layers.65.mlp.gate",
	"model.layers.66.self_attn.indexer.weights_proj",
	"model.layers.66.mlp.gate",
	"model.layers.67.mlp.gate",
	"model.layers.68.mlp.gate",
	"model.layers.69.mlp.gate",
	"model.layers.70.self_attn.indexer.weights_proj",
	"model.layers.70.mlp.gate",
	"model.layers.71.mlp.gate",
	"model.layers.72.mlp.gate",
	"model.layers.73.mlp.gate",
	"model.layers.74.self_attn.indexer.weights_proj",
	"model.layers.74.mlp.gate",
	"model.layers.75.mlp.gate",
	"model.layers.76.mlp.gate",
	"model.layers.77.mlp.gate",
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.15.1.dev22+g792acec"
	},
	"rms_norm_eps": 1e-05,
	"rope_interleave": true,
	"rope_parameters": {
	"rope_theta": 8000000,
	"rope_type": "default"
	},
	"routed_scaling_factor": 2.5,
	"scoring_func": "sigmoid",
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"transformers_version": "5.13.0.dev0",
	"use_cache": true,
	"v_head_dim": 256,
	"vocab_size": 154880
	}