nvidia / text-generation updated 5 months ago

GLM-5-NVFP4

Name: GLM-5-NVFP4
Author: nvidia

The NVIDIA GLM-5 NVFP4 model is the quantized version of ZAI’s GLM-5 model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA GLM-5 NVFP4 model is quantized with Model Optimizer.

Params

435.2 B

Context

202,752

Downloads 30d

189 K

Likes

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

Download history

daily snapshots · 51 days

▲ 0 in the last 30 days (0.0%)

189 K159 K

Aug 2Aug 19Sep 5Sep 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	u8	480.8 GB	594.6 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 198K ctx	480.8 GB	2,145.2 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-nvfp4
{
  "hf_id": "nvidia/GLM-5-NVFP4",
  "params_b": 435.24,
  "context_length": 202752,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 188640,
  "vram_estimates": [
    { "quant": "u8", "gb": 594.6 }
  ],
  "updated_at": "2026-08-02T01:00:35Z"
}

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

Specifications

Architecture: GlmMoeDsaForCausalLM
Parameters: 435.2 B
Tensor type: U8
Context length: 202,752
Vocabulary: 154,880
Layers / heads: 78 / 64
Licence: mit
First seen on the Hub: 2026-02-24
Base model: GLM-5
Training datasets: undisclosed
Added to our catalog: 2026-08-02

Family

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

Base GLM-5 zai-org 157 K

Compare with any text-generation model

Popular comparisons

gpt-oss-120b 5.0 M DeepSeek-V4-Flash-0731 4.1 M DeepSeek-V3.2 2.5 M GLM-5.2-FP8 978 K DeepSeek-R1 773 K GLM-5.2-NVFP4 751 K