zai-org / text-generation Open weights Also via API updated 2 months ago

GLM-5.2

Name: GLM-5.2
Price: 0.006 USD
Author: zai-org

👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.2 blog and GLM-5 Technical report. 📍 Use GLM-5.2 API services on Z.ai API Platform. 🔜 Try GLM-5.2 here.

Params

753.3 B

Context

1,048,576

Downloads 30d

320 K

Likes

5,206

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

Download history

daily snapshots · 106 days

▲ 328 K in the last 30 days (50.6%)

2.8 M263 K

Jul 28Sep 1Oct 6Nov 10

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	bf16	1,506.7 GB	1,770.8 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 1024K ctx	1,506.7 GB	16,121.8 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-5-2
{
  "hf_id": "zai-org/GLM-5.2",
  "params_b": 753.33,
  "context_length": 1048576,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 320374,
  "vram_estimates": [
    { "quant": "bf16", "gb": 1770.8 }
  ],
  "updated_at": "2026-09-02T01:00:12Z"
}

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

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.006

input / 1M

$6.80

output / 1M

$0.005

cached input / 1M

$6.81

1M in + 1M out

:batch variant $0.57 in · $1.17 out

Context window: 1,048,576 tokens
Max output: 943,718 tokens
Providers: 24
Cheapest provider: DeepInfra · $0.45 / $1.44
Best throughput: —
AA Intelligence / Coding / Agentic: — / 68.8 / 38.4

✓ Tool calling ✓ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✓ Prompt caching

Specifications

Architecture: GlmMoeDsaForCausalLM
Parameters: 753.3 B
Tensor type: BF16
Context length: 1,048,576
Vocabulary: 154,880
Layers / heads: 78 / 64
Licence: mit
First seen on the Hub: 2026-06-16
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Derivative GLM-5.2-AWQ-INT4 cyankiwi 196 K Derivative GLM-5.2-NVFP4 nvidia 147 K Derivative GLM-5.2-GGUF unsloth 145 K

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 7.6 M DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF 3.3 M GLM-5.3 2.0 M DeepSeek-R1 1.6 M DeepSeek-V3 1.5 M GLM-5 1.4 M