GLM-5.3-NVFP4
The NVIDIA GLM-5.3 NVFP4 model is the quantized version of ZAI's GLM-5.3 model, which is an auto-regressive language model that uses an optimized transformer architecture. GLM-5.3 is a Mixture-of-Experts (MoE) model for reasoning, coding, and agentic tasks; it uses the same base model as GLM-5.2, with gains from post-training, and uses sparse attention (with an IndexShare indexer) to support a long context. For more...
Params
753.3 B
Context
1,048,576
Downloads 30d
237 K
Likes
48
Download history
daily snapshots · 8 days237 K150 K
Nov 3Nov 5Nov 8Nov 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 | u8 | 464.1 GB | 624.1 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 464.1 GB | 14,975.0 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 -s https://aimodelscomparison.com/api/v1/models/glm-5-3-nvfp4
{
"hf_id": "nvidia/GLM-5.3-NVFP4",
"params_b": 753.33,
"context_length": 1048576,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 237499,
"vram_estimates": [
{ "quant": "u8", "gb": 624.1 }
],
"updated_at": "2026-11-03T01:00:15Z"
}
Specifications
- Architecture
- GlmMoeDsaForCausalLM
- Parameters
- 753.3 B
- Tensor type
- U8
- Context length
- 1,048,576
- Vocabulary
- 154,880
- Layers / heads
- 78 / 64
- Licence
- other
- First seen on the Hub
- 2026-09-14
- Base model
- GLM-5.3
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-03
Compare with any text-generation model