GLM 4.7 REAP 218B A32B i1 needs about 135.4 GB of memory at Q4_K_M (a 131.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.4 GB to 179.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.3 GB.
GLM 4.7 REAP 218B A32B i1 is a 218B-parameter GLM model in GGUF format, quantized by mradermacher. Its trained context length is 198K tokens. The repository has 24 quant files, from 0.4 GB to 179.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 4.0 GB | Fits | Get file → | |
| IQ1_S | 44.3 GB | 47.9 GB | Too big | Get file → | |
| IQ1_M | 49.1 GB | 52.7 GB | Too big | Get file → | |
| IQ2_XXS | 57.2 GB | 60.8 GB | Too big | Get file → | |
| IQ2_XS | 63.9 GB | 67.5 GB | Too big | Get file → | |
| IQ2_S | 65.1 GB | 68.7 GB | Too big | Get file → | |
| IQ2_M | 71.6 GB | 75.2 GB | Too big | Get file → | |
| Q2_K_S | 73.8 GB | 77.4 GB | Too big | Get file → | |
| Q2_K | 79.8 GB | 83.4 GB | Too big | Get file → | |
| IQ3_XXS | 84.0 GB | 87.6 GB | Too big | Get file → | |
| IQ3_XS | 89.1 GB | 92.7 GB | Too big | Get file → | |
| Q3_K_S | 94.3 GB | 97.9 GB | Too big | Get file → | |
| IQ3_S | 94.4 GB | 98.0 GB | Too big | Get file → | |
| IQ3_M | 96.0 GB | 99.6 GB | Too big | Get file → | |
| Q3_K_M | 104.4 GB | 108.0 GB | Too big | Get file → | |
| Q3_K_L | 113.5 GB | 117.1 GB | Too big | Get file → | |
| IQ4_XS | 116.5 GB | 120.1 GB | Too big | Get file → | |
| Q4_0 | 123.6 GB | 127.2 GB | Too big | Get file → | |
| Q4_K_S | 124.0 GB | 127.6 GB | Too big | Get file → | |
| Q4_K_M | 131.8 GB | 135.4 GB | Too big | Get file → | |
| Q4_1 | 136.8 GB | 140.4 GB | Too big | Get file → | |
| Q5_K_S | 150.4 GB | 154.0 GB | Too big | Get file → | |
| Q5_K_M | 154.8 GB | 158.4 GB | Too big | Get file → | |
| Q6_K | 179.3 GB | 182.9 GB | Too big | Get file → |
What GPU do you need for GLM 4.7 REAP 218B A32B i1?
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: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 4.0 GB in use).
- 48 GB VRAM: the best quant that fits is IQ1_S (44.3 GB file, about 47.9 GB in use).
Which GLM 4.7 REAP 218B A32B i1 quant should you choose?
Q4_K_M is the usual starting point for GLM 4.7 REAP 218B A32B i1: it balances file size and quality well. Here it is a 131.8 GB file.
If memory is tight, the smallest file is the first one in the table at 0.4 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 4.7 REAP 218B A32B i1
How much VRAM does GLM 4.7 REAP 218B A32B i1 need?
About 135.4 GB at Q4_K_M with an 8K context window. That is the 131.8 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 4.7 REAP 218B A32B i1 on an 8 GB GPU?
Yes, with the smaller files: the 0.4 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4.7 REAP 218B A32B i1 GGUF?
It depends on the quant: file is 0.4 GB, IQ1_S is 44.3 GB, IQ1_M is 49.1 GB, IQ2_XXS is 57.2 GB, IQ2_XS is 63.9 GB, IQ2_S is 65.1 GB and 18 more.
What context length does GLM 4.7 REAP 218B A32B i1 support?
The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 3.1 GB at 8K and 12.3 GB at 32K.
Where can I download GLM 4.7 REAP 218B A32B i1 GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.7-REAP-218B-A32B-i1-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 4.7 REAP 218B A32B i1 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.