ukisai/Swift-Qwen3.8-27B-GGUF — new model trending #30 on Hugging Face
UkisAI released Swift-Qwen3.8-27B GGUF, a Qwen3.8-27B derivative cutting thinking tokens by 58.3% with under 1% performance loss and roughly 1.95x speedup.
UkisAI released Swift-Qwen3.8-27B as GGUF on Hugging Face, a reasoning-efficient derivative of Qwen3.8-27B using a Swift adapter that reduces median thinking tokens by up to 58.3% while keeping performance losses under 1% and delivering a 1.95x speed-up on several tasks. Reported benchmarks include GPQA-Diamond 88.28%, MMLU-Pro 84.95%, C-Eval 90.62%, AIME 2026 94.00% and Terminal-Bench 2.1 65.84%. The model is trending at #30 on Hugging Face, with BF16 weights and enterprise licensing also available.
- Cuts median thinking tokens by 58.3% on GPQA-Diamond versus the Qwen3.8-27B base with only a 0.10-point score drop.
- Delivers a 1.95x speed-up on several tasks while maintaining near-identical performance.
- Benchmarks include GPQA-Diamond 88.28%, MMLU-Pro 84.95%, AIME 2026 94.00% and Terminal-Bench 2.1 65.84%.
- Released as GGUF quantization on Hugging Face, trending at #30; BF16 weights and enterprise licensing also offered.
- Vendors
- UkisAI
- Products
- Swift-Qwen3.8-27B
- Organizations
- Hugging Face
- AI models
- Swift-Qwen3.8-27BQwen3.8-27B
From the original article
6 min read at huggingface.coimage-text-to-text · 36,615 downloads · 156 likes · license other
By ukisai · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.