GLM 4.7 Flash REAP 23B A3B absolute heresy i1 needs about 15.3 GB of memory at Q4_K_M (a 13.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.1 GB to 18.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM‑4.7‑Flash‑REAP‑23B‑A3B: a 23B sparse MoE model compressed by 25%
GLM‑4.7‑Flash‑REAP‑23B‑A3B is a 23B parameter sparse Mixture‑of‑Experts model with 3B active parameters per token. It was created using REAP pruning and retains core capabilities of the full GLM‑4.7‑Flash. The model supports a context length of 202,752 tokens and is released under the MIT license.
Good at
- Sparse MoE inference
- Large context handling
- Code generation
Limits
- Requires 8‑k context for memory estimates
- No vision support
- Mixture‑of‑Experts architecture
Best for
- Local deployment with limited VRAM
- Academic research on MoE models
- Fine‑tuning on specialized datasets
Who it’s for. Developers and researchers who need a memory‑efficient GLM‑4.7‑Flash variant for local inference. The model is suitable for environments where VRAM is limited but a large context is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 4.8 GB | 6.2 GB | Fits | Get file → | |
| IQ1_M | 5.3 GB | 6.7 GB | Fits | Get file → | |
| IQ2_XXS | 6.2 GB | 7.5 GB | Tight | Get file → | |
| IQ2_XS | 6.9 GB | 8.2 GB | Too big | Get file → | |
| IQ2_S | 7.0 GB | 8.3 GB | Too big | Get file → | |
| IQ2_M | 7.7 GB | 9.0 GB | Too big | Get file → | |
| Q2_K_S | 7.9 GB | 9.2 GB | Too big | Get file → | |
| Q2_K | 8.5 GB | 9.9 GB | Too big | Get file → | |
| IQ3_XXS | 9.0 GB | 10.3 GB | Too big | Get file → | |
| IQ3_XS | 9.5 GB | 10.9 GB | Too big | Get file → | |
| IQ3_S | 10.0 GB | 11.4 GB | Too big | Get file → | |
| Q3_K_S | 10.0 GB | 11.4 GB | Too big | Get file → | |
| IQ3_M | 10.2 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_M | 11.1 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_L | 12.0 GB | 13.3 GB | Too big | Get file → | |
| IQ4_XS | 12.3 GB | 13.7 GB | Too big | Get file → | |
| Q4_0 | 13.1 GB | 14.4 GB | Too big | Get file → | |
| Q4_K_S | 13.1 GB | 14.5 GB | Too big | Get file → | |
| Q4_K_M | 13.9 GB | 15.3 GB | Too big | Get file → | |
| Q4_1 | 14.5 GB | 15.8 GB | Too big | Get file → | |
| Q5_K_S | 15.9 GB | 17.2 GB | Too big | Get file → | |
| Q5_K_M | 16.3 GB | 17.7 GB | Too big | Get file → | |
| Q6_K | 18.9 GB | 20.2 GB | Too big | Get file → |
For 8‑GB VRAM, use the IQ1_S quant (4.83 GB file, 6.2 GB memory at 8k context). If 12‑GB VRAM is available, Q4_K_M (13.93 GB file, 15.3 GB memory) offers higher quality. For the lowest memory footprint, the unknown quant (0.06 GB file, 1.4 GB memory) is suitable but may lack full functionality.
What GPU do you need for GLM 4.7 Flash REAP 23B A3B absolute heresy 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 (0.1 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_XXS (6.2 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_M (10.2 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_1 (14.5 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (18.9 GB file, about 20.2 GB in use).
Which GLM 4.7 Flash REAP 23B A3B absolute heresy i1 quant should you choose?
Q4_K_M is the usual starting point for GLM 4.7 Flash REAP 23B A3B absolute heresy i1: it balances file size and quality well. Here it is a 13.9 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 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
Frequently asked questions about GLM 4.7 Flash REAP 23B A3B absolute heresy i1
How much VRAM does GLM 4.7 Flash REAP 23B A3B absolute heresy i1 need?
About 15.3 GB at Q4_K_M with an 8K context window. That is the 13.9 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 Flash REAP 23B A3B absolute heresy i1 on an 8 GB GPU?
Yes, with IQ2_XXS: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4.7 Flash REAP 23B A3B absolute heresy i1 GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.2 GB, IQ2_XS is 6.9 GB, IQ2_S is 7.0 GB and 18 more.
What context length does GLM 4.7 Flash REAP 23B A3B absolute heresy 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 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download GLM 4.7 Flash REAP 23B A3B absolute heresy i1 GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.7-Flash-REAP-23B-A3B-absolute-heresy-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 Flash REAP 23B A3B absolute heresy 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.
Can I run this model on 8 GB VRAM?
Yes, the IQ1_S quant requires about 6.2 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.