DavidAU / image-text-to-text updated 4 days ago

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

Name: Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
Author: DavidAU

Important: This is the first fine tune to exceed 730 "arc-c" ("735": 144 pts higher than Qwen 3.8 27B) AND 880 ARC-E (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and over 718 arc-c in 4 bit. This version is called TURBO because it drastically reduces thinking tokens (by 1/2 to as high as 1/10), yet maintains output detail and quality. In otherwords while "reg" Qwen3.8 27B is thinking about "formatt...

Params

—

Context

—

Downloads 30d

1.3 M

Likes

1,002

Commercial use: allowed apache-2.0 Not gated GGUF 2 languages View on Hugging Face ↗

Download history

daily snapshots · 7 days

1.3 M876 K

Sep 15Sep 17Sep 19Sep 21

Can you run it?

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

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-IQ2_M.gguf	IQ2_M	12.1 GB	13.8 GB	✅ Runs comfortably
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-IQ3_M.gguf	IQ3_M	14.5 GB	16.5 GB	✅ Runs comfortably
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-IQ4_XS.gguf	IQ4_XS	17.0 GB	19.2 GB	✅ Runs comfortably
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q4_K_S.gguf	Q4_K_S	17.5 GB	19.8 GB	⚠️ Tight — reduce context
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q4_K_M.gguf	Q4_K_M	18.5 GB	20.8 GB	⚠️ Tight — reduce context
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q5_K_S.gguf	Q5_K_S	20.6 GB	23.2 GB	⚠️ Tight — reduce context
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q5_K_M.gguf	Q5_K_M	21.2 GB	23.8 GB	⚠️ Tight — reduce context
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q6_K.gguf	Q6_K	24.0 GB	26.9 GB	❌ Won’t fit

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: 2026-09-01
Training datasets: DavidAU/Polar-STRICT-Datasets, DavidAU/F451-STRICT-Datasets
Added to our catalog: 2026-09-15

Compare with any image-text-to-text model

Popular comparisons

Qwen3-VL-8B-Instruct 19.7 M gemma-4-26B-A4B-it 10.0 M Qwen3.6-35B-A3B-FP8 9.5 M Qwen3.5-9B 9.2 M gemma-4-31B-it 9.0 M Qwen3.8-27B 7.3 M