Videos

Qwen 3.8 Flash Next, served by the Strata engine on a roughly $1,000 secondhand build, generated a fully interactive...

Multiple fine-tuned versions of Qwen 3.8-27B now claim to reduce thinking tokens by 37-58% while maintaining...

Qwen 27B's 381 tok/s on a single RTX 3090 is only achievable when the model is copying text already present in the...

An untouched one-bit Qwen 3.8 27B jumps from 29% to 61.5% on MMLU Pro and cuts time-to-first-token from 12.27 to...

Alibaba's Zhenru 900 beats Nvidia's H200 on paper in exactly two published specs, 216GB memory versus 141GB and a...

Strata, an Engine 1 developer's inference engine for Qwen-3 8B Flash Next, claims 44.8 tokens/second on a 12GB RTX...

A public record investigation by Transloose documents AI agents persistently probing websites over months, including...

Qwen Image 2.1 generates decent local images on a 4090, but the real story is using Hermes Agent to iteratively...

Bonsai 2 compresses Qwen 3.8 from 54GB to 5.9GB using ternary quantization (1.76 bits per weight), claiming 98%...

Bonsai 2 27B's ternary quantization claims 98% quality retention at 9x smaller size, but in practice the quality...

Prism ML's Bonsai 2 27B is a heavily quantized version of Qwen 3.8 27B that fits on a single GPU with 12-16 GB VRAM,...

Edge Zero's 2.9 GB memory claim for running Qwen 3.6 35B is technically accurate but misleading: it measures what...

Neo Horse's post-training improved Qwen's agent performance without moving to a larger model, with the 4B model's...

Two 8.4 GB GGUF files of Qwen 3.8 27B differ by 7.7 points on average benchmarks because one uses a new quantization...

Qwen 3.8 Flash Next running in a Hermes agent on a quad-3090 setup achieves 55-60 tokens per second with a Q4...

Qwen 3 Flash Next at Q4 quantization shows noticeably weaker visual reasoning than the full-precision Qwen3 27B,...

Qwen3.8-Flash-Next's 51B 'engram' parameters are a lookup table designed to live in slow host memory, not on the...

Qwen 3.8 Flash Next, a preview of the Qwen 4 architecture, can run on a quad-RTX 3090 rig with 96GB VRAM using...

Qwen3.8 Flash Next, a preview of the Qwen 4 architecture, demonstrates exceptional vision and code generation...

Qwen 3.8 27B, a 27-billion-parameter model from Alibaba, achieves benchmark scores near GPT-5.6 Luna and Opus 4.6...

The visible difference between Pi Agent and OpenCode running the same Qwen 3.8 model on a simple one-shot task is...

Ornith 1.5 35B-A3B, a Mixture of Experts model based on Qwen 3.5, shows impressive capability for its size,...

Qwen released the 27B parameter Qwen3.8-27B model, which significantly outperforms its predecessor Qwen3.6-27B and...

Qwen's 27B model ships with a multi-token prediction head that can nearly triple throughput for free—no extra...

Alibaba's Qwen 3.8-27B replaces 75% of its attention layers with Gated DeltaNet, slashing KV cache memory from 244...

Alibaba's Qwen 3.8 27B dense model claims to beat Opus 4.6 on several coding benchmarks while being Apache 2.0...

Qwen 3.8 27B is a powerful local AI model that can run on a single GPU, showing impressive results in coding, game...

Qwen 3.8 27B is a huge leap over 3.6 for local AI agentic coding. In a zero-shot test, it built three playable retro...

Qwen 3.8 (27B model) drops in 20 hours and promises to redefine local AI, but the creator's AC failing at the worst...

QAC is a local AI SDK that lets you install and run multiple AI models (speech-to-text, embeddings, LLM,...

Alibaba announced the Qwen 3.8 Max Preview, a 2.4 trillion parameter open-weight model claiming performance second...

Prism ML's Bonsai 27B models (ternary and 1-bit) dramatically shrink a Qwen 3.6 27B base while retaining surprising...

Ornith 1.0, a family of fine-tuned local coding models (9B dense and 35B MoE variants tested), shows promising...