GLM 5.3 Flash REAP50 FP8 v2 needs about 129.6 GB of memory at Q3_K_M (a 79.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 61.4 GB (Q2_K) to 94.4 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 197.6 GB.
GLM 5.3 Flash REAP50 FP8 v2 is a 165B-parameter GLM model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 6 quant files, from 61.4 GB (Q2_K) to 94.4 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 61.4 GB | 111.3 GB | Too big | Get file → | |
| Q3_K_S | 72.4 GB | 122.2 GB | Too big | Get file → | |
| Q3_K_M | 79.7 GB | 129.6 GB | Too big | Get file → | |
| Q3_K_L | 86.7 GB | 136.6 GB | Too big | Get file → | |
| IQ4_XS | 89.3 GB | 139.2 GB | Too big | Get file → | |
| Q4_K_S | 94.4 GB | 144.3 GB | Too big | Get file → |
What GPU do you need for GLM 5.3 Flash REAP50 FP8 v2?
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 REAP50 FP8 v2 quant should you choose?
Q3_K_M (79.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 61.4 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
Frequently asked questions about GLM 5.3 Flash REAP50 FP8 v2
How much VRAM does GLM 5.3 Flash REAP50 FP8 v2 need?
About 129.6 GB at Q3_K_M with an 8K context window. That is the 79.7 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 REAP50 FP8 v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 111.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 5.3 Flash REAP50 FP8 v2 GGUF?
It depends on the quant: Q2_K is 61.4 GB, Q3_K_S is 72.4 GB, Q3_K_M is 79.7 GB, Q3_K_L is 86.7 GB, IQ4_XS is 89.3 GB, Q4_K_S is 94.4 GB.
What context length does GLM 5.3 Flash REAP50 FP8 v2 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 49.4 GB at 8K and 197.6 GB at 32K.
Where can I download GLM 5.3 Flash REAP50 FP8 v2 GGUF?
The files are on Hugging Face in the mradermacher/GLM-5.3-Flash-REAP50-FP8-v2-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 REAP50 FP8 v2 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.