dtometzki/GLM-4.7-Flash-FP8-Dynamic

GLM-4.7-Flash

<div align="center"> <img src=https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/logo.svg width="15%"/> </div> <p align="center"> 👋 Join our <a href="https://discord.gg/QR7SARHRxK" target="blank">Discord</a> community. <br> 📖 Check out the GLM-4.7 <a href="https://z.ai/blog/glm-4.7" target="blank">technical blog</a>, <a href="https://arxiv.org/abs/2508.06471" target="_blank">technical report(GLM-4.5)</a>. <br> 📍 Use GLM-4.7-Flash API services on <a href="https://docs.z.ai/guides/llm/glm-4.7">Z.ai API Platform. </a> <br> 👉 One click to <a href="https://chat.z.ai">GLM-4.7</a>. </p>

Introduction

GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

Performances on Benchmarks

Evaluation Parameters

Default Settings (Most Tasks)

• —temperature: 1.0
• —top-p: 0.95
• —max new tokens: 131072

For multi-turn agentic tasks (τ²-Bench and Terminal Bench 2), please turn on Preserved Thinking mode.

Terminal Bench, SWE Bench Verified

• —temperature: 0.7
• —top-p: 1.0
• —max new tokens: 16384

τ^2-Bench

• —Temperature: 0
• —Max new tokens: 16384

For τ^2-Bench evaluation, we added an additional prompt to the Retail and Telecom user interaction to avoid failure modes caused by users ending the interaction incorrectly. For the Airline domain, we applied the domain fixes as proposed in the Claude Opus 4.5 release report.

Serve GLM-4.7-Flash Locally

For local deployment, GLM-4.7-Flash supports inference frameworks including vLLM and SGLang. Comprehensive deployment instructions are available in the official Github repository.

vLLM and SGLang only support GLM-4.7-Flash on their main branches.

vLLM

• —using pip (must use pypi.org as the index url):

pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly
pip install git+https://github.com/huggingface/transformers.git

SGLang

• —Install the supported versions of SGLang and Transformers (using uv is recommended):

uv pip install sglang==0.3.2.dev9039+pr-17247.g90c446848 --extra-index-url https://sgl-project.github.io/whl/pr/
uv pip install git+https://github.com/huggingface/transformers.git@76732b4e7120808ff989edbd16401f61fa6a0afa

transformers

using with transformers as

pip install git+https://github.com/huggingface/transformers.git

and then run:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_PATH = "zai-org/GLM-4.7-Flash"
messages = [{"role": "user", "content": "hello"}]
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
)
model = AutoModelForCausalLM.from_pretrained(
    pretrained_model_name_or_path=MODEL_PATH,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
inputs = inputs.to(model.device)
generated_ids = model.generate(**inputs, max_new_tokens=128, do_sample=False)
output_text = tokenizer.decode(generated_ids[0][inputs.input_ids.shape[1]:])
print(output_text)

vLLM

vllm serve dtometzki/GLM-4.7-Flash-FP8-Dynamic \
     --speculative-config.method mtp \
     --speculative-config.num_speculative_tokens 1 \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \
     --served-model-name glm-4.7-flash