DavidAU / image-text-to-text updated 3 days ago

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

ABSOLUTE FIRE: 640 ARC-C for both 8bit and 4bit. Model exceeds 7 of 7 benchmarks for Qwen 3.5 9B, Qwen3.5 27B, Qwen3.6 35B-A3B, and meets Qwen 3.6 27B in some cases... and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided. (this model is part of the Qwen 3.6 27B Fable Fusion 711 pipelines: 2200+ likes, 3 million + downloads)

Params
Context
Downloads 30d
1.5 M
Likes
734
Commercial use: allowed apache-2.0 Not gated GGUF 2 languages View on Hugging Face ↗

Download history

daily snapshots · 26 days
1.5 M865 K
Aug 26Sep 3Sep 12Sep 20

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
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ2_M.gguf IQ2_M 4.9 GB 5.9 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ3_M.gguf IQ3_M 5.7 GB 6.8 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_XS.gguf IQ4_XS 6.5 GB 7.7 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_NL.gguf IQ4_NL 6.8 GB 7.9 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-Q4_K_S.gguf Q4_K_S 6.7 GB 7.9 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-Q4_K_M.gguf Q4_K_M 7.0 GB 8.2 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-Q5_K_S.gguf Q5_K_S 7.7 GB 8.9 GB ✅ Runs comfortably
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-Q5_K_M.gguf Q5_K_M 7.8 GB 9.1 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
apache-2.0
First seen on the Hub
2026-07-19
Training datasets
undisclosed
Added to our catalog
2026-08-26
Compare with any image-text-to-text model