Instructions to use RedHatAI/GLM-5.2-MXFP4xMXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/GLM-5.2-MXFP4xMXFP8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/GLM-5.2-MXFP4xMXFP8")
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-MXFP4xMXFP8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/GLM-5.2-MXFP4xMXFP8", 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 RedHatAI/GLM-5.2-MXFP4xMXFP8 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-MXFP4xMXFP8"
# 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-MXFP4xMXFP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/GLM-5.2-MXFP4xMXFP8

SGLang

How to use RedHatAI/GLM-5.2-MXFP4xMXFP8 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-MXFP4xMXFP8" \
    --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-MXFP4xMXFP8",
		"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-MXFP4xMXFP8" \
        --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-MXFP4xMXFP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/GLM-5.2-MXFP4xMXFP8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/GLM-5.2-MXFP4xMXFP8
```

GLM-5.2-MXFP4xMXFP8 / config.json

kylesayrs

Upload folder using huggingface_hub

0e84af2 verified 3 days ago

Raw

History Blame Contribute Delete

5.18 kB

	{
	"architectures": [
	"GlmMoeDsaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"ep_size": 1,
	"first_k_dense_replace": 3,
	"head_dim": 192,
	"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_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,
	"moe_router_dtype": "float32",
	"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": {
	"config_group_0": {
	"format": "mxfp4-pack-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": 32,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": "torch.uint8",
	"strategy": "group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 32,
	"num_bits": 4,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": "torch.uint8",
	"strategy": "group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "mxfp4-pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"model.embed_tokens",
	"re:^model\\.layers\\.[0-2]\\..*",
	"re:.self_attn.",
	"re:.mlp\\.gate.",
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"transform_config": {},
	"version": "0.17.2.dev32+g46196ce"
	},
	"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": "5.12.0",
	"use_cache": true,
	"v_head_dim": 256,
	"vocab_size": 154880
	}