zai-org / text-generation updated 5 months ago

GLM-5-FP8

Name: GLM-5-FP8
Author: zai-org

👋 Join our WeChat or Discord community. 📖 Check out the GLM-5 Technical report. 📍 Use GLM-5 API services on Z.ai API Platform. 👉 One click to GLM-5.

Params

753.9 B

Context

202,752

Downloads 30d

203 K

Likes

182

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

Download history

daily snapshots · 56 days

▲ 792 K in the last 30 days (79.6%)

1.3 M203 K

Jul 28Aug 15Sep 3Sep 21

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	756.2 GB	945.4 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 198K ctx	756.2 GB	3,631.2 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-5-fp8
{
  "hf_id": "zai-org/GLM-5-FP8",
  "params_b": 753.91,
  "context_length": 202752,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 202976,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 945.4 }
  ],
  "updated_at": "2026-07-28T18:03:15Z"
}

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

Specifications

Architecture: GlmMoeDsaForCausalLM
Parameters: 753.9 B
Tensor type: F8_E4M3
Context length: 202,752
Vocabulary: 154,880
Layers / heads: 78 / 64
Licence: mit
First seen on the Hub: 2026-02-11
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-generation model

Popular comparisons

DeepSeek-V4-Flash-0731 4.1 M DeepSeek-V3.2 2.5 M GLM-5.2-FP8 978 K GLM-5.2 962 K Qwen3-235B-A22B 348 K MiniMax-M3-NVFP4 186 K