GLM 5.3 UNCENSORED FP8 needs about 456.5 GB of memory at Q4_K_M (a 454.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 315.9 GB (Q2_K) to 825.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
GLM 5.3 UNCENSORED FP8 – 790 B parameter mixture‑of‑experts model
GLM 5.3 UNCENSORED FP8 is a 790 B parameter mixture‑of‑experts model converted to GGUF. It supports up to 1 048 576 context tokens and is released under the MIT license. The model is available in several quantizations from Q2_K to Q8_0.
Good at
- Large context reasoning
- Uncensored general‑purpose responses
- High token capacity
Limits
- No vision support
- Requires large VRAM for higher quants
- Reasoning loops need low setting
Best for
- Long‑form content generation
- Complex reasoning tasks
- Research prototyping
Who it’s for. Developers and researchers needing a large, uncensored language model with extensive context. Suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 315.9 GB (18 parts) | 317.8 GB | Too big | Get file → | |
| Q3_K_M | 397.7 GB (22 parts) | 399.6 GB | Too big | Get file → | |
| Q4_K_M | 454.6 GB (27 parts) | 456.5 GB | Too big | Get file → | |
| Q6_K | 648.9 GB (39 parts) | 650.8 GB | Too big | Get file → | |
| Q8_0 | 825.0 GB (47 parts) | 826.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (≈318 GB memory estimate). For 16 GB VRAM, Q3_K_M (≈400 GB). For 32 GB VRAM, Q4_K_M (≈457 GB). Higher quants need proportionally more memory.
What GPU do you need for GLM 5.3 UNCENSORED FP8?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which GLM 5.3 UNCENSORED FP8 quant should you choose?
Q4_K_M is the usual starting point for GLM 5.3 UNCENSORED FP8: it balances file size and quality well. Here it is a 454.6 GB file.
The Q8_0 file is 825.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 315.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 5.3 UNCENSORED FP8
How much VRAM does GLM 5.3 UNCENSORED FP8 need?
About 456.5 GB at Q4_K_M with an 8K context window. That is the 454.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run GLM 5.3 UNCENSORED FP8 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 317.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 5.3 UNCENSORED FP8 GGUF?
It depends on the quant: Q2_K is 315.9 GB, Q3_K_M is 397.7 GB, Q4_K_M is 454.6 GB, Q6_K is 648.9 GB, Q8_0 is 825.0 GB.
What context length does GLM 5.3 UNCENSORED FP8 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download GLM 5.3 UNCENSORED FP8 GGUF?
The files are on Hugging Face in the softwareweaver/GLM-5.3-Uncensored-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GLM 5.3 UNCENSORED FP8 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run GLM 5.3 UNCENSORED FP8 on 8 GB VRAM?
Only the Q2_K quant is feasible, requiring about 318 GB of VRAM at 8 k context, which exceeds 8 GB. It is not practical on 8 GB VRAM.
Does this model support vision inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.