GL

cerebras/GLM-4.7-Flash-REAP-23B-A3B

GLMGGUF by unslothUpdated 2026-01-28
Download on Hugging Face
Parameters23B
Context198K
Layers47
Architecturedeepseek2
Smallest quant6.5 GB
Quick answer

cerebras/GLM-4.7-Flash-REAP-23B-A3B needs about 15.5 GB of memory at Q4_K_M (a 14.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 27 quants, from 6.5 GB (TQ1_0) to 46.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM‑4.7‑Flash‑REAP‑23B‑A3B: a 25% lighter, near‑lossless compressed GLM model

GLM‑4.7‑Flash‑REAP‑23B‑A3B is a sparse Mixture‑of‑Experts causal language model with 23 B total parameters and 3 B active per token. It retains the full 202,752‑token context length of the base GLM‑4.7‑Flash while reducing memory usage by 25 % through REAP pruning.

Good at

  • Near‑lossless code generation
  • Agentic workflows
  • Function calling

Limits

  • Requires 8 k context for memory estimates
  • No vision support
  • MIT license limits commercial use to MIT terms

Best for

  • Local deployment on limited GPU memory
  • Academic research on MoE models
  • Code generation tasks

Who it’s for. Developers and researchers who need a compact GLM model that keeps the performance of the larger 30 B variant. The model is ideal for environments with constrained GPU memory and for use cases that rely on code generation, agentic workflows, and function calling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_06.5 GB 7.9 GB
Tight Get file →
IQ1_S7.2 GB 8.5 GB
Too big Get file →
IQ1_M7.6 GB 8.9 GB
Too big Get file →
IQ2_XXS8.2 GB 9.6 GB
Too big Get file →
IQ2_M8.6 GB 9.9 GB
Too big Get file →
Q2_K8.8 GB 10.1 GB
Too big Get file →
Q2_K_L8.8 GB 10.2 GB
Too big Get file →
Q2_K_XL9.0 GB 10.4 GB
Too big Get file →
IQ3_XXS10.0 GB 11.4 GB
Too big Get file →
Q3_K_S10.3 GB 11.6 GB
Too big Get file →
Q3_K_M11.3 GB 12.6 GB
Too big Get file →
Q3_K_XL11.5 GB 12.8 GB
Too big Get file →
IQ4_XS12.6 GB 13.9 GB
Too big Get file →
IQ4_NL13.3 GB 14.6 GB
Too big Get file →
Q4_013.3 GB 14.6 GB
Too big Get file →
Q4_K_S13.3 GB 14.7 GB
Too big Get file →
Q4_K_M14.1 GB 15.5 GB
Too big Get file →
Q4_K_XL14.2 GB 15.6 GB
Too big Get file →
Q4_114.6 GB 16.0 GB
Too big Get file →
Q5_K_S16.0 GB 17.4 GB
Too big Get file →
Q5_K_M16.5 GB 17.8 GB
Too big Get file →
Q5_K_XL16.7 GB 18.1 GB
Too big Get file →
Q6_K19.0 GB 20.3 GB
Too big Get file →
Q6_K_XL20.2 GB 21.6 GB
Too big Get file →
Q8_024.5 GB 25.8 GB
Too big Get file →
Q8_K_XL27.5 GB 28.9 GB
Too big Get file →
BF1646.0 GB 47.3 GB
Too big Get file →

For 8 GB VRAM, the Q4_0 quant (~14.6 GB file) is the smallest that fits, using about 15.5 GB of VRAM at 8 k context. If 12 GB VRAM is available, Q4_K_M (~14.11 GB file) uses ~15.5 GB VRAM. For 16 GB VRAM, Q5_K_S (~16.04 GB file) uses ~17.4 GB VRAM, which is still within budget with some headroom.

What GPU do you need for cerebras/GLM-4.7-Flash-REAP-23B-A3B?

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: the best quant that fits is TQ1_0 (6.5 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_S (10.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (14.6 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_XL (20.2 GB file, about 21.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_K_XL (27.5 GB file, about 28.9 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (46.0 GB file, about 47.3 GB in use).

Which cerebras/GLM-4.7-Flash-REAP-23B-A3B quant should you choose?

Q4_K_M is the usual starting point for cerebras/GLM-4.7-Flash-REAP-23B-A3B: it balances file size and quality well. Here it is a 14.1 GB file.

The Q8_0 file is 24.5 GB, about 1.7 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 TQ1_0 at 6.5 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters23B (approximate, mixture of experts)
Active parameters3B
Layers47
Trained context202,752 tokens
KV cache (fp16)100 KB per token

Source

Quantized byunsloth
FamilyGLM
Licensemit
Downloads (HF)23,413
Last updated2026-01-28

Frequently asked questions about cerebras/GLM-4.7-Flash-REAP-23B-A3B

How much VRAM does cerebras/GLM-4.7-Flash-REAP-23B-A3B need?

About 15.5 GB at Q4_K_M with an 8K context window. That is the 14.1 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 cerebras/GLM-4.7-Flash-REAP-23B-A3B on an 8 GB GPU?

Yes, with TQ1_0: the 6.5 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cerebras/GLM-4.7-Flash-REAP-23B-A3B GGUF?

It depends on the quant: TQ1_0 is 6.5 GB, IQ1_S is 7.2 GB, IQ1_M is 7.6 GB, IQ2_XXS is 8.2 GB, IQ2_M is 8.6 GB, Q2_K is 8.8 GB and 21 more.

What context length does cerebras/GLM-4.7-Flash-REAP-23B-A3B 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 cerebras/GLM-4.7-Flash-REAP-23B-A3B GGUF?

The files are on Hugging Face in the unsloth/GLM-4.7-Flash-REAP-23B-A3B-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 cerebras/GLM-4.7-Flash-REAP-23B-A3B 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 GLM‑4.7‑Flash‑REAP‑23B‑A3B on 8 GB VRAM?

The smallest quant that fits 8 GB VRAM is Q4_0, which requires about 15.5 GB VRAM at 8 k context, so 8 GB is insufficient.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of GLM-4.7-Flash-REAP-23B-A3B

Similar models

Browse all →

More from unsloth

All by unsloth →

More GLM models

All GLM →

Other medium models

All medium models →