GLM 5.3 Flash Coder needs about 151.5 GB of memory at Q4_K_M (a 102.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 47.4 GB (IQ2_XXS) to 180.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 193.3 GB.
GLM 5.3 Flash Coder is a 170B-parameter GLM model in GGUF format, quantized by diablomike20. Its trained context length is 1024K tokens. The repository has 5 quant files, from 47.4 GB (IQ2_XXS) to 180.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 47.4 GB | 96.3 GB | Too big | Get file → | |
| IQ2_XXS | 50.8 GB (2 parts) | 99.6 GB | Too big | Get file → | |
| Q3_K_M | 75.1 GB (2 parts) | 123.9 GB | Too big | Get file → | |
| Q4_K_M | 102.6 GB (3 parts) | 151.5 GB | Too big | Get file → | |
| Q8_0 | 180.4 GB (4 parts) | 229.2 GB | Too big | Get file → |
What GPU do you need for GLM 5.3 Flash Coder?
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 Flash Coder quant should you choose?
Q4_K_M is the usual starting point for GLM 5.3 Flash Coder: it balances file size and quality well. Here it is a 102.6 GB file.
The Q8_0 file is 180.4 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 IQ2_XXS at 47.4 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 Flash Coder
How much VRAM does GLM 5.3 Flash Coder need?
About 151.5 GB at Q4_K_M with an 8K context window. That is the 102.6 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 Coder on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 96.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 5.3 Flash Coder GGUF?
It depends on the quant: IQ2_XXS is 47.4 GB, IQ2_XXS is 50.8 GB, Q3_K_M is 75.1 GB, Q4_K_M is 102.6 GB, Q8_0 is 180.4 GB.
What context length does GLM 5.3 Flash Coder 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 48.3 GB at 8K and 193.3 GB at 32K.
Where can I download GLM 5.3 Flash Coder GGUF?
The files are on Hugging Face in the diablomike20/GLM-5.3-Flash-Coder-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 Flash Coder 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.