GL

GLM 4.7 REAP 268B A32B i1

GLMGGUF by mradermacherUpdated 2026-01-27
Download on Hugging Face
Parameters269B
Context198K
Layers92
Architectureglm4moe
Smallest quant0.4 GB
Quick answer

GLM 4.7 REAP 268B A32B i1 needs about 165.8 GB of memory at Q4_K_M (a 162.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.4 GB to 190.6 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 12.3 GB.

GLM 4.7 REAP 268B A32B i1 – a memory‑efficient sparse MoE model

GLM‑4.7‑REAP‑268B‑A32B is a 268B‑parameter sparse mixture‑of‑experts model compressed from the 355B base. It retains near‑lossless performance on code generation, agentic workflows, and function calling while reducing memory usage by 25%. The model is released under the MIT license.

Good at

  • Reasoning
  • Tool usage
  • Sparse expert inference

Limits

  • Requires 8k context for memory estimates
  • No vision support
  • Large VRAM needed for high‑bit quants

Best for

  • Local deployment on resource‑constrained hardware
  • Academic research on MoE models
  • Fine‑tuning with limited GPU memory

Who it’s for. Researchers and developers who need a large‑scale language model with reduced memory footprint. The model is compatible with vanilla vLLM and can be run locally with appropriate GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 4.0 GB
Fits Get file →
IQ1_S54.3 GB 57.9 GB
Too big Get file →
IQ1_M60.3 GB 63.9 GB
Too big Get file →
IQ2_XXS70.3 GB 73.9 GB
Too big Get file →
IQ2_XS78.5 GB 82.1 GB
Too big Get file →
IQ2_S79.8 GB 83.4 GB
Too big Get file →
IQ2_M87.9 GB 91.5 GB
Too big Get file →
Q2_K_S90.7 GB 94.3 GB
Too big Get file →
Q2_K98.1 GB 101.7 GB
Too big Get file →
IQ3_XXS103.4 GB 106.9 GB
Too big Get file →
IQ3_XS109.6 GB 113.2 GB
Too big Get file →
Q3_K_S116.0 GB 119.6 GB
Too big Get file →
IQ3_S116.1 GB 119.7 GB
Too big Get file →
IQ3_M117.9 GB 121.5 GB
Too big Get file →
Q3_K_M128.4 GB 132.0 GB
Too big Get file →
Q3_K_L139.5 GB 143.1 GB
Too big Get file →
IQ4_XS143.3 GB 146.9 GB
Too big Get file →
Q4_0152.1 GB 155.7 GB
Too big Get file →
Q4_K_S152.6 GB 156.2 GB
Too big Get file →
Q4_K_M162.3 GB 165.8 GB
Too big Get file →
Q4_1168.3 GB 171.9 GB
Too big Get file →
Q5_K_S185.1 GB 188.7 GB
Too big Get file →
Q5_K_M190.6 GB 194.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (54.28 GB file, 57.9 GB memory at 8k context). For 16 GB VRAM, IQ1_M (60.3 GB file, 63.9 GB memory). For 32 GB VRAM, Q4_K_M (162.26 GB file, 165.8 GB memory). Estimates are approximate.

What GPU do you need for GLM 4.7 REAP 268B 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 the main file (0.4 GB file, about 4.0 GB in use).

Which GLM 4.7 REAP 268B A32B i1 quant should you choose?

Q4_K_M is the usual starting point for GLM 4.7 REAP 268B A32B i1: it balances file size and quality well. Here it is a 162.3 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

Architectureglm4moe
Parameters269B (approximate, mixture of experts)
Active parameters32B
Layers92
Trained context202,752 tokens
KV cache (fp16)368 KB per token

Source

Quantized bymradermacher
FamilyGLM
Licensemit
Downloads (HF)884
Last updated2026-01-27

Frequently asked questions about GLM 4.7 REAP 268B A32B i1

How much VRAM does GLM 4.7 REAP 268B A32B i1 need?

About 165.8 GB at Q4_K_M with an 8K context window. That is the 162.3 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 268B 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 268B A32B i1 GGUF?

It depends on the quant: file is 0.4 GB, IQ1_S is 54.3 GB, IQ1_M is 60.3 GB, IQ2_XXS is 70.3 GB, IQ2_XS is 78.5 GB, IQ2_S is 79.8 GB and 17 more.

What context length does GLM 4.7 REAP 268B 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 268B A32B i1 GGUF?

The files are on Hugging Face in the mradermacher/GLM-4.7-REAP-268B-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 268B 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.

Can I run this model on 8 GB VRAM?

The smallest quant for 8 GB VRAM is IQ1_S, which requires about 57.9 GB of memory at 8k context, so it is not feasible on 8 GB VRAM.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of GLM-4.7-REAP-268B-A32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More GLM models

All GLM →

Other large models

All large models →