ConwayResearch/Underdog-Saluki-27B-1.0 — new model trending #30 on Hugging Face
Underdog Saluki 27B 1.0 is a 7.89 GB GGUF of Qwen3.8-27B that retains tool calling for llama.cpp.
45
Organization
ISTA-DASLab
- Mentions · 7d0
- Mentions · 30d0
- All mentions6
- First seenSep 7, 2026
- Last mentionedOct 8, 2026
Timeline
6 articles · newest firstSC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF — new model trending #30 on Hugging Face
SC117 published abliterated GGUF quants of Qwen3.8-Flash-Next that swap 144 tensors while keeping GSQ-RCO scales.
34
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF — new model trending #30 on Hugging Face
ISTA-DASLab published a 50-percent expert-pruned Qwen3.8 coder weighing 58.4 GB in GGUF.
44
ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF — new model trending #30 on Hugging Face
UkisAI published GSQ-RCO GGUF quantizations of Swift 1.5 Qwen3.8-27B, from 8.42 GB to 11.77 GB.
48
Shapelearn Qwen 3.8 27B (13.1 GB VRAM)
ByteShape released full ShapeLearn GGUF quants of Qwen 3.8 27B; its GPU-5 IQ4_XS reaches 99.63% of BF16 quality at 13.1 GB VRAM.
30
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF — new model trending #30 on Hugging Face
ISTA-DASLab releases GSQ-RCO non-uniform GGUF quantizations of Qwen3.8-Flash-Next, a 512-expert multimodal MoE, at 2.4-3.0 bits per weight.
42
Appears with
- llama.cppproduct · 4
- Qwen3.8-27Bai model · 3
- Qwen3.8-Flash-Nextai model · 3
- Hugging Faceorganization · 2
- GGUFproduct · 2
- LM Studioproduct · 1
- Qwenorganization · 1
- Underdog-Saluki-27B-1.0ai model · 1
- Institute of Science and Technology Austriavendor · 1
- SC117organization · 1
- Qwenvendor · 1
- Swift 1.5 Qwen3.8-27Bai model · 1
- Qwen3.8-Flash-Next-GSQ-RCO-Coderai model · 1
- Underdogorganization · 1
- Qwen3.8-Flash-Next-GSQ-RCO-abliteratedai model · 1
- Alibabavendor · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.