Search: “bf16”

7 stories in the last 7d

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.

Hugging Face trending modelsSep 11, 14:58 UTC · 5d agoModel release

How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus

Reproduction study finds Orthrus speculative-decoding trajectories match the reference model in only ~45% of cases under BF16, but 100% under FP32.

Researchers independently reproduced Orthrus, a hybrid autoregressive-diffusion architecture claiming lossless speculative decoding via intra-model consensus, testing exact trajectory matching on 1,190 prompts across 12 domains. Under BF16, exact matching occurred in only 45% of cases for the authors' checkpoint and 43% for an independently trained model, with matching probability strongly tied to reference-model response-conditional perplexity. Despite trajectory divergence, downstream lm-eval-harness benchmarks showed no systematic degradation, while FP32 evaluation yielded exact matching on all prompts.

Hugging Face daily papersSep 13, 20:00 UTC · 3d agoAI research1

Agnes-AI/Agnes-3.0-Flash — new model trending #30 on Hugging Face

Agnes AI releases open-weight Agnes-3.0-Flash Preview, a 33B multimodal model with 262k-token context under Apache 2.0.

Agnes AI released Agnes-3.0-Flash Preview, an open-weights multimodal checkpoint with 33B parameters and a 262,144-token context window under Apache 2.0. The model supports text, image, and video understanding, tool calling, and adjustable reasoning effort. The repo clarifies this preview checkpoint is distinct from the production/API Agnes 3.0 Flash model, which uses a different configuration with a 1M-token context window. Reported reference results include IFBench 74.20 and SciCode 38.08 against peers such as Qwen3.6-35B-A3B, Kimi K2.5, and MiniMax M3.

Hugging Face trending modelsSep 11, 15:50 UTC · 5d agoModel release

Comfy-Org/YuE2 — new model trending #30 on Hugging Face

m-a-p's YuE2-3B music generation model and SheetSage2 audio encoder are repackaged in bf16 for ComfyUI and trending #30 on Hugging Face.

Comfy-Org published repackaged bf16 safetensors files for m-a-p's YuE2-3B model and its SheetSage2 audio encoder, organized into ComfyUI checkpoints and audio encoder folders. The repository links to the original m-a-p/YuE2-3B and m-a-p/SheetSage2 model pages and is currently trending #30 on Hugging Face.

Hugging Face trending modelsSep 11, 03:35 UTC · 6d agoModel release 2 sources

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

VC-Attention is a training-free low-bit attention method for diffusion transformers, achieving 1.46-1.59x kernel speedups on datacenter GPUs with higher fidelity.

VC-Attention is a training-free low-bit attention framework for diffusion transformers that pairs V-Smooth value smoothing via lightweight online clustering with ExpCast-FP8, which maps log-domain scores directly to E4M3 FP8 probability codes and eliminates the FP32 softmax exponential. It is implemented for B200, B300, H200, RTX PRO 6000, and RTX 5090 GPUs. Across Wan2.2, LongCat-Video, HunyuanVideo-1.5, and MiniMax-H3, it improves fidelity over low-bit baselines and speeds attention 1.46-1.59x over BF16 FlashAttention-4 on datacenter Blackwell and Hopper GPUs and 2.3-3.6x on workstation cards, with 1.13-1.70x faster end-to-end clip generation.

Hugging Face daily papersupdated 00:45 UTC · 4h agofirst Sep 13, 20:00 UTC · 3d agoAI research 2 sources

Cohere Releases North Small Translate: A 218B MoE Translation Model That Scores 83.6 on WMT26 Across 50 Languages

Cohere released North Small Translate, an open-weight 218B MoE (25B active) translation model scoring 83.6 on WMT26 across 50 languages.

Cohere and Cohere Labs released North Small Translate, a decoder-only sparse Mixture-of-Experts translation model with 218B total and 25B active parameters, 128 experts with 8 activated per token plus shared experts, and 16K-token input and output context. In Cohere's vendor-reported WMT26 evaluation, judged by GPT-5.6-Sol, it scores 83.6 averaged across 50 languages (84.36 in an agentic multi-pass mode), ahead of DeepL NextGen (81.37), Qwen 3.5 397B A17B (81.56), GLM 5.2 (76.50), and Google Translate (68.20). The model was built with RWS's Language Weaver team, post-trained specifically for translation, and reports 112 output tokens per second versus 81 for Gemma 4 31B, with long-document xCOMET-XL scores of 48.9 versus 21.3 for Google Translate. It is available free on Cohere's Chat V2 API until rate limits, with three self-hosting checkpoints including a 4-bit NVFP4 variant running on 1x B200 or 2x H100.

MarkTechPostSep 11, 06:57 UTC · 5d agoModel release

Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

Cognition released SWE-2, a coding model post-trained from Kimi K3 that scores 50.0% on FrontierCode 1.1 Main, near Fable 5.1 at 64% lower cost.

Cognition introduced SWE-2, its most advanced coding model, post-trained from the 2.8T-parameter Kimi K3 base model. It achieves 50.0% on FrontierCode 1.1 Main, 73.0% on DeepSWE 1.1, and 92.8% on Terminal-Bench 2.1, beating Grok 4.6 and SWE-1.7 while matching Fable 5.1 and GPT-5.6 Sol at a fraction of the price. The company says it scaled reinforcement learning to the multi-trillion-parameter regime for the first time, using Pareto-informed cost penalties that train all reasoning-effort levels in a single run, tripled RL environments, and NVFP4/FP8 quantization-aware training. SWE-2 is available today in Devin Desktop and CLI, with rollout on Devin Web and Fusion.

Hacker News · AIupdated Sep 12, 20:00 UTC · 4d agofirst Sep 10, 15:29 UTC · 6d agoModel release 11 sources HN 58↑ · 15 comments1