nvidia / text-generation updated 1 month ago

GLM-5.2-NVFP4

Name: GLM-5.2-NVFP4
Author: nvidia

The NVIDIA GLM-5.2 NVFP4 model is the quantized version of ZAI’s GLM-5.2 model, which is an auto-regressive language model that uses an optimized transformer architecture. GLM-5.2 is a Mixture-of-Experts (MoE) model for reasoning and coding that uses sparse attention (with an IndexShare indexer) to support a long context. For more information, please check here. The NVIDIA GLM-5.2 NVFP4 model is quantized with Model...

Params

381.0 B

Context

1,048,576

Downloads 30d

1.8 M

Likes

305

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

Download history

daily snapshots · 10 days

1.8 M1.6 M

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	u8	464.8 GB	569.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 1024K ctx	464.8 GB	7,826.8 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-nvfp4
{
  "hf_id": "nvidia/GLM-5.2-NVFP4",
  "params_b": 380.99,
  "context_length": 1048576,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 1804344,
  "vram_estimates": [
    { "quant": "u8", "gb": 569.0 }
  ],
  "updated_at": "2026-07-28T18:03:03Z"
}

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

Specifications

Architecture: GlmMoeDsaForCausalLM
Parameters: 381.0 B
Tensor type: U8
Context length: 1,048,576
Vocabulary: 154,880
Layers / heads: 78 / 64
Licence: mit
First seen on the Hub: 2026-06-22
Base model: GLM-5.2
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base GLM-5.2 zai-org 2.2 M

Compare with

DeepSeek-R1 9.9 M gpt-oss-120b 4.2 M DeepSeek-V4-Flash 2.7 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M DeepSeek-V3.2 1.2 M

Appears in

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