Alibaba's Qwen3.8-Flash-Next Shrinks 125B Model to 84 GiB on One Machine
A community quant of Qwen3.8-Flash-Next shrinks the 177B MoE to 84 GiB with a per-layer mixed-precision recipe that beats standard IQ4_XS on both size and quality.
// Intelligence
Gpus
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
AngelSlim Shrinks Tencent's 1.5TB Hy4-Preview to 214 GiB at 6x Compression
Tencent's AngelSlim team shrinks the 770B Hy4-preview MoE from 1.5TB down to 213GB using a custom 1.31-bit quantization strategy with minimal accuracy loss.
UNSEEN Gemma 4 Removes AI Refusals With a Single Math Trick
A 26B multimodal Gemma variant with refusal directions surgically removed lands on Hugging Face in GGUF format, ready for llama.cpp.
SuperQwen3.8 Runs Uncensored on One Box at 1.77x Faster Speeds
A community fine-tune of Qwen3.8-27B strips refusals, fixes the resulting weight damage, and ships in four formats tuned for local inference.
Qwen3.8-27B Hits 417 tok/s on a Single RTX 3090 With 150k Context
A community project squeezes Qwen3.8-27B onto a 24GB gaming card with vLLM, hitting 417 tok/s batched or 82 tok/s single-user at 150k context.
Red Hat Shrinks GLM-5.3-Flash to 4-Bit for NVIDIA Blackwell GPUs
Red Hat AI shipped an NVFP4 quantization of Z.ai's 320B GLM-5.3-Flash, shrinking the model to run on vLLM with FP4 activations while holding reasoning benchmarks near the original.
vLLM v0.28.0 Ships Sparse Attention and 60% Faster Speculative Decoding
The latest vLLM release lands 584 commits from 270 contributors, with big performance wins for Kimi-K3, DeepSeek-V4, and speculative decoding.
Cerebras Unveils CS-4 Roadmap Targeting 30x Faster AI Than GPUs
Cerebras unveiled the CS-4 wafer-scale system architecture at Hot Chips and sketched a roadmap to CS-5 and 3D-stacked DRAM in CS-6.
NVIDIA's Dynamo Cuts LLM Engine Crash Recovery from 283 Seconds to 7
NVIDIA Dynamo's new shadow engine keeps a warm standby ready on the same GPU, cutting LLM failover from minutes to seconds.
Exo Turns Four Mac Studios Into a 4.8TB/s AI Cluster
Apple officially endorsed exo on its Mac Studio and Mac Mini pages, blessing a workflow that turns four desktops into a 4.8TB/s inference rig.
OpenAI's Jalapeño Chip Beats Nvidia's Best on Inference by 3.6x
OpenAI's first in-house inference chip delivers 1.5-1.9x more work per watt and up to 4.1x lower latency versus current systems.
NVIDIA's Groq 3 LPX Hits 4x Faster Inference at 100K Context
NVIDIA's new inference accelerator hit 3,431 tokens/second on Gemma 4 31B at 100K context, roughly 4x the fastest public endpoint in third-party testing.
Liquid AI's Pipette Exposes What Server Benchmarks Hide About Phone AI
Liquid AI and Artificial Analysis release an open-source suite that measures model quality, speed, latency, and memory across real phones, laptops, and embedded hardware.
Qwen Drops Qwen3.8-Flash-Next, a 125B Open Model That Activates Only 6B Parameters
Qwen ships an FP8 preview of the architecture behind Qwen4, pairing sparse attention, n-gram embeddings and 125B params with 6B active.
Qwen3.8 Hits 49 Tokens per Second on AMD's Budget APU
A community quantization pairs a 27B Qwen model with multi-token prediction and AMD's IU4 matrix path, hitting ~49 tokens per second on a single Strix Halo APU.
Solo Creator Grafts Z-Image Textures Into MiniMax-H3 Without Any Training
A community-made checkpoint grafts Z-Image's texture attention onto MiniMax H3's video engine, giving richer surfaces without retraining or extra VRAM.
AEON vLLM Ultimate Fixes NVIDIA DGX Spark's Broken AI Stack in One Pull
A community-built vLLM container brings NVFP4 KV cache, DFlash speculative decoding, and Blackwell sm_121a runtime patches to DGX Spark serving.
Qwen3.8-27B Unleashed Hits 83% MMLU Uncensored on a Single 24GB GPU
A per-tensor dynamic quantization of an abliterated Qwen3.8-27B lands on Hugging Face, delivering 82.98% MMLU and 262k context on a single RTX 4090.
No stories match these filters.