Model Intelligence Sheet
iasarkar/GLM-5.2-BF16-GGUF overview
GLM 5.2 BF16 GGUF BF16 GGUF of Z.ai's GLM 5.2 https://huggingface.co/zai org/GLM 5.2 745B MoE, 40B active, 1M context . Base for making your own quants without…
Runs locally from ~116.86 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
8 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| glm52-bf16-split-00001-of-00008.gguf | GGUF | BF16 | 182.55 GB | Download |
| glm52-bf16-split-00002-of-00008.gguf | GGUF | BF16 | 184.62 GB | Download |
| glm52-bf16-split-00003-of-00008.gguf | GGUF | BF16 | 183.87 GB | Download |
| glm52-bf16-split-00004-of-00008.gguf | GGUF | BF16 | 183.89 GB | Download |
| glm52-bf16-split-00005-of-00008.gguf | GGUF | BF16 | 183.87 GB | Download |
| glm52-bf16-split-00006-of-00008.gguf | GGUF | BF16 | 183.89 GB | Download |
| glm52-bf16-split-00007-of-00008.gguf | GGUF | BF16 | 183.87 GB | Download |
| glm52-bf16-split-00008-of-00008.gguf | GGUF | BF16 | 116.86 GB | Download |
Model Details
| Model ID | iasarkar/GLM-5.2-BF16-GGUF |
|---|---|
| Author | iasarkar |
| Pipeline | text-generation |
| License | mit |
| Base model | zai-org/GLM-5.2 |
| Last modified | 2026-06-26T05:00:18.000Z |
Model README
---
base_model: zai-org/GLM-5.2
base_model_relation: quantized
license: mit
language:
- en
- zh
tags:
- glm
- moe
- gguf
- bf16
- llama-cpp
pipeline_tag: text-generation
---
GLM-5.2 BF16 GGUF
BF16 GGUF of Z.ai's GLM-5.2 (745B MoE, 40B active, 1M context). Base for making your own quants without the 3-hour conversion.
Model Details
- Base model: zai-org/GLM-5.2
- Format: Split GGUF (8 shards)
- Precision: BF16 (no quantization loss)
- Total size: ~1.51TB
- License: MIT (same as base model)
Produced by
Run iasarkar/GLM-5.2-BF16-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models