QW

Qwopus GLM 18B Merged

QwenGGUF by JackrongUpdated 2026-07-09
Download on Hugging Face
Parameters15.9B
Context256K
Layers64
Architectureqwen35
Smallest quant9.8 GB
Quick answer

Qwopus GLM 18B Merged needs about 12.5 GB of memory at Q4_K_M (a 9.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 9.8 GB (Q4_K_M) to 16.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Qwopus GLM 18B Merged – a 18B parameter Qwen model with merged 32-layer stacks

Qwopus GLM 18B Merged is a 64‑layer frankenmerge of two Qwen3.5‑9B finetunes, producing an ~18B parameter model. It was healed with a 1000‑step LoRA fine‑tune to smooth the layer boundary. The model is trained on high‑quality reasoning data derived from GLM‑5.1.

Good at

  • Coding
  • Reasoning
  • Tool usage

Limits

  • No vision support
  • Requires large VRAM for full context
  • Experimental model may have quirks

Best for

  • Complex code generation
  • Structured reasoning tasks
  • Instruction following

Who it’s for. Developers and researchers needing a mid‑size Qwen model that balances performance and GPU memory. It is suitable for users with 12–16 GB GPUs who want better code and reasoning than the 9B variant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M9.8 GB 12.5 GB
Too big Get file →
Q5_K_M11.4 GB 14.0 GB
Too big Get file →
Q6_K13.0 GB 15.7 GB
Too big Get file →
Q8_016.9 GB 19.5 GB
Too big Get file →

For 12–16 GB VRAM, use the Q4_K_M quant (file size 9.84 GB, estimated 12.5 GB memory at 8k context). If more memory is available, Q5_K_M (11.39 GB, 14 GB memory) or Q6_K (13.04 GB, 15.7 GB memory) can be used. Q8_0 requires 16.88 GB and 19.5 GB memory, which may exceed typical consumer GPUs.

What GPU do you need for Qwopus GLM 18B Merged?

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 Q6_K (13.0 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.9 GB file, about 19.5 GB in use).

Which Qwopus GLM 18B Merged quant should you choose?

Q4_K_M is the usual starting point for Qwopus GLM 18B Merged: it balances file size and quality well. Here it is a 9.8 GB file.

The Q8_0 file is 16.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters15.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byJackrong
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,860
Last updated2026-07-09

Frequently asked questions about Qwopus GLM 18B Merged

How much VRAM does Qwopus GLM 18B Merged need?

About 12.5 GB at Q4_K_M with an 8K context window. That is the 9.8 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 Qwopus GLM 18B Merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwopus GLM 18B Merged GGUF?

It depends on the quant: Q4_K_M is 9.8 GB, Q5_K_M is 11.4 GB, Q6_K is 13.0 GB, Q8_0 is 16.9 GB.

What context length does Qwopus GLM 18B Merged support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Qwopus GLM 18B Merged GGUF?

The files are on Hugging Face in the Jackrong/Qwopus-GLM-18B-Merged-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 Qwopus GLM 18B Merged use?

Hugging Face lists the license as apache-2.0. 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, Q4_K_M, requires about 12.5 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does this model support image input?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3.5-9B-GLM5.1-Distill-v1

Similar models

Browse all →

More from Jackrong

All by Jackrong →

More Qwen models

All Qwen →

Other medium models

All medium models →