KyleHessling1 / text-generation updated 5 months ago

Qwopus-GLM-18B-Merged-GGUF

A 64-layer frankenmerge of two of Jackrong's incredible Qwen3.5-9B finetunes, stacking all 32 layers from each to create an ~18B parameter model, then healed with a 1000-step QLoRA fine-tune to smooth the layer boundary.

Params
Context
Downloads 30d
295 K
Likes
119
Commercial use: allowed apache-2.0 Not gated GGUF 7 languages View on Hugging Face ↗

Download history

daily snapshots · 30 days
318 K190 K
Aug 23Sep 2Sep 12Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Qwopus-GLM-18B-Healed-Q3_K_M.gguf Q3_K_M 7.9 GB 9.2 GB ✅ Runs comfortably
Qwopus-GLM-18B-Healed-Q4_K_M.gguf Q4_K_M 9.8 GB 11.3 GB ✅ Runs comfortably
Qwopus-GLM-18B-Healed-Q5_K_M.gguf Q5_K_M 11.5 GB 13.1 GB ✅ Runs comfortably
Qwopus-GLM-18B-Healed-Q6_K.gguf Q6_K 13.0 GB 14.8 GB ✅ Runs comfortably
Qwopus-GLM-18B-Healed-Q8_0.gguf Q8_0 16.9 GB 19.1 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_K_M
$ ollama run qwopus-glm-18b-merged-gguf

# pin the quantization explicitly
$ ollama run qwopus-glm-18b-merged-gguf-q4_k_m
est. VRAM 11.3 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2026-04-17
Training datasets
undisclosed
Added to our catalog
2026-08-23
Compare with any text-generation model