zai-org / text-generation updated 11 months ago

GLM-4.5-Air-FP8

Name: GLM-4.5-Air-FP8
Author: zai-org

👋 Join our Discord community. 📖 Check out the GLM-4.5 technical blog, technical report, and Zhipu AI technical documentation. Code on GitHub 📍 Use GLM-4.5 API services on Z.ai API Platform (Global) or Zhipu AI Open Platform (Mainland China). 👉 One click to GLM-4.5.

Params

110.5 B

Context

131,072

Downloads 30d

168 K

Likes

Commercial use: allowed mit Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

168 K156 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	112.6 GB	140.9 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	112.6 GB	389.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/glm-4-5-air-fp8
{
  "hf_id": "zai-org/GLM-4.5-Air-FP8",
  "params_b": 110.51,
  "context_length": 131072,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 168319,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 140.9 }
  ],
  "updated_at": "2026-07-28T18:09:16Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Glm4MoeForCausalLM
Parameters: 110.5 B
Tensor type: F8_E4M3
Context length: 131,072
Vocabulary: 151,552
Layers / heads: 46 / 96
Licence: mit
First seen on the Hub: 2025-07-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M DeepSeek-V4-Flash 2.7 M Qwen3-Coder-Next-FP8 2.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB