GLM 5.3 Flash BF16 needs about 127.8 GB of memory at IQ2_S (a 113.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 0.5 GB to 154.8 GB.
GLM 5.3 Flash BF16 – 321 B parameter language model
GLM 5.3 Flash BF16 is a 321 B parameter model from the GLM family. It is available in several quantized GGUF files, ranging from 0.51 GB to 154.83 GB. The model supports deployment with llama.cpp and other frameworks.
Good at
- Large‑scale language tasks
- Efficient inference with low‑precision quants
- Versatile framework support
Limits
- No vision support in the base GGUF
- Large memory requirement for high‑precision quants
- License and usage terms not specified
Best for
- Chat applications needing high capacity
- Research on large‑language‑model inference
- Benchmarking low‑precision quantization
Who it’s for. Developers and researchers who need a large language model that can be run locally with quantization. The model is suitable for those who can manage the memory demands of the larger quants and are comfortable using llama.cpp or other compatible frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ2_XXS | 92.9 GB (2 parts) | 104.5 GB | Too big | Get file → | |
| IQ2_S | 113.6 GB (3 parts) | 127.8 GB | Too big | Get file → | |
| Q2_K | 128.3 GB (3 parts) | 144.2 GB | Too big | Get file → | |
| — | 144.3 GB (3 parts) | 162.1 GB | Too big | Get file → | |
| — | 154.8 GB (4 parts) | 173.9 GB | Too big | Get file → |
For 8 GB VRAM, use the 0.51 GB unknown quant (est. 1.1 GB memory). For 16 GB VRAM, the 92.86 GB IQ2_XXS quant (est. 104.5 GB memory) is the smallest available. For 32 GB VRAM, the 113.62 GB IQ2_S quant (est. 127.8 GB memory) is recommended. Memory estimates are approximate.
What GPU do you need for GLM 5.3 Flash BF16?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
Which GLM 5.3 Flash BF16 quant should you choose?
IQ2_S (113.6 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 5.3 Flash BF16
How much VRAM does GLM 5.3 Flash BF16 need?
About 127.8 GB at IQ2_S with an 8K context window. That is the 113.6 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 Flash BF16 on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 5.3 Flash BF16 GGUF?
It depends on the quant: file is 0.5 GB, IQ2_XXS is 92.9 GB, IQ2_S is 113.6 GB, Q2_K is 128.3 GB, file is 144.3 GB, file is 154.8 GB.
Where can I download GLM 5.3 Flash BF16 GGUF?
The files are on Hugging Face in the avar6/GLM-5.3-Flash-BF16-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run GLM 5.3 Flash BF16 on 8 GB VRAM?
The smallest GGUF file is 0.51 GB and requires about 1.1 GB memory at 8k context, so it fits in 8 GB VRAM.
Does the model support vision tasks?
The base GGUF files do not include vision support; the repo notes experimental vision support requires a special llama.cpp fork.
What quantization options are available?
Available quants are unknown, IQ2_XXS, IQ2_S, Q2_K, and larger unknowns up to 154.83 GB.