GL

GLM 4.7 Flash REAP 23B A3B ROCmFP4

GLMGGUF by cafonezUpdated 2026-06-07
Download on Hugging Face
Parameters23B
Context198K
Layers47
Architecturedeepseek2
Smallest quant12.3 GB
Quick answer

GLM 4.7 Flash REAP 23B A3B ROCmFP4 needs about 13.6 GB of memory at BF16 (a 12.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM 4.7 Flash REAP 23B A3B ROCmFP4 is a 23B-parameter GLM model in GGUF format, quantized by cafonez. Its trained context length is 198K tokens. The repository has 1 quant file, from 12.3 GB (BF16) to 12.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1612.3 GB 13.6 GB
Too big Get file →

What GPU do you need for GLM 4.7 Flash REAP 23B A3B ROCmFP4?

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: the best quant that fits is BF16 (12.3 GB file, about 13.6 GB in use).

Which GLM 4.7 Flash REAP 23B A3B ROCmFP4 quant should you choose?

BF16 (12.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 bycafonez
FamilyGLM
Licenseother
Downloads (HF)205
Last updated2026-06-07

Frequently asked questions about GLM 4.7 Flash REAP 23B A3B ROCmFP4

How much VRAM does GLM 4.7 Flash REAP 23B A3B ROCmFP4 need?

About 13.6 GB at BF16 with an 8K context window. That is the 12.3 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 Flash REAP 23B A3B ROCmFP4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.7 Flash REAP 23B A3B ROCmFP4 GGUF?

It depends on the quant: BF16 is 12.3 GB.

What context length does GLM 4.7 Flash REAP 23B A3B ROCmFP4 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 ROCmFP4 GGUF?

The files are on Hugging Face in the cafonez/GLM-4.7-Flash-REAP-23B-A3B-ROCmFP4-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 ROCmFP4 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of GLM-4.7-Flash

Similar models

Browse all →

More from cafonez

All by cafonez →

More GLM models

All GLM →

Other medium models

All medium models →