Model index / Qwen / Qwen3.8-Flash-Next-GSQ-RCO-abliterated
Qwen / MODEL PROFILE
Qwen3.8-Flash-Next-GSQ-RCO-abliterated
SC117 · Published release · Abliteration · GGUF
Model source
Published by SC117 on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.
Declared base model
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF ↗
Hardware and context
The parameter count cannot be determined from current metadata, so no VRAM estimate is provided. KV cache, context length, multimodal components and concurrency increase actual memory usage.
Context length: Not stated in public metadata. Please consult the model card.
Download sources and quantized variants
10 repositories| HUGGING FACE REPOSITORY | Format | 30-day downloads | Declared license |
|---|---|---|---|
| SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF ↗ | GGUF | 2.9M | apache-2.0 |
| DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF ↗ | GGUF | 75.3K | apache-2.0 |
| cc1244578151/Qwen3.8-Flash-Next-Abliterated-Uncensored-GGUF ↗ | GGUF | 10K | apache-2.0 |
| shefowl/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-Hybrid-GGUF ↗ | GGUF | 6K | other |
| DatKurai/Qwen3.8-Flash-Next-GSQ-RCO-Coder-Uncen-IQ1_M-GGUF ↗ | GGUF | 3.9K | apache-2.0 |
| shefowl/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-Hybrid-352E-4050-16GB-Generalist-GGUF ↗ | GGUF | 2.3K | other |
| zugquants/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-z-GGUF ↗ | GGUF | 1.1K | apache-2.0 |
| zugquants/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF ↗ | GGUF | 294 | apache-2.0 |
| AItaro0214/qwen38-flash-next-abliterated-iq3s ↗ | GGUF | 61 | apache-2.0 |
| minpei/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-Strata-pack ↗ | GGUF | 0 | apache-2.0 |
Uncensored is a publisher description, not a guarantee of zero refusals, capability, accuracy or safety. This index does not measure refusal rates or performance benchmarks.
More from this family
More Qwen →Qwen27B ↗
Qwen3.8-27B-abliterated
huihui-ai
↓ 3.1M ♡ 2.6K~16.5 GB ↗
Qwen27B ↗
Qwen3.8-27B-Uncensored
JonathanColetti
↓ 2.7M ♡ 2.3K~16.5 GB ↗
Qwen27B ↗
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP
HauhauCS
↓ 2.6M ♡ 2.4K~16.5 GB ↗
QwenSize not stated ↗
Qwen-Image-2.1-Uncensored-Quantized
abenzerps
↓ 2.2M ♡ 5.2KVRAM unknown ↗