zai-org / image-text-to-text updated 1 week ago

GLM-5.3-Flash

Name: GLM-5.3-Flash
Author: zai-org

👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report. 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.

Params

321.3 B

Context

—

Downloads 30d

2.9 M

Likes

2,480

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

Download history

daily snapshots · 22 days

2.9 M190 K

Aug 30Sep 6Sep 13Sep 20

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	328.3 GB	409.9 GB	❌ Won’t fit

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

Specifications

Architecture: Glm5NextForConditionalGeneration
Parameters: 321.3 B
Tensor type: F8_E4M3
Licence: mit
First seen on the Hub: 2026-08-25
Training datasets: undisclosed
Added to our catalog: 2026-08-30

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative GLM-5.3-Flash-GGUF unsloth 630 K

Compare with any image-text-to-text model

Popular comparisons

Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 4.0 M Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 2.3 M Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 1.9 M Qwen3.5-9B-GGUF 1.5 M Qwen3.8-Flash-Next-GGUF 1.5 M Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 1.5 M

Appears in

Fastest-growing VLMs