zai-org / text-generation updated 2 weeks ago

GLM-5.3

Name: GLM-5.3
Author: zai-org

GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks:

Params

753.3 B

Context

1,048,576

Downloads 30d

947 K

Likes

1,886

Licence: other Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 16 days

947 K304 K

Sep 5Sep 10Sep 15Sep 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	755.6 GB	944.7 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 1024K ctx	755.6 GB	15,295.6 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-5-3
{
  "hf_id": "zai-org/GLM-5.3",
  "params_b": 753.33,
  "context_length": 1048576,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 947261,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 944.7 }
  ],
  "updated_at": "2026-09-05T01:00:17Z"
}

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

Specifications

Architecture: GlmMoeDsaForCausalLM
Parameters: 753.3 B
Tensor type: F8_E4M3
Context length: 1,048,576
Vocabulary: 154,880
Layers / heads: 78 / 64
Licence: other
First seen on the Hub: 2026-08-25
Training datasets: undisclosed
Added to our catalog: 2026-09-05

Family

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

Derivative GLM-5.3-GGUF unsloth 492 K

Compare with any text-generation model

Popular comparisons

DeepSeek-V4-Flash-0731 4.2 M DeepSeek-V3.2 2.4 M DeepSeek-V3 1.1 M DeepSeek-V3-0324 991 K GLM-5.2-FP8 986 K GLM-5.2 974 K

Appears in

Trending text-generation