QWEN 3.8 27B Q8 Quant - Setup Instructions Help
Hi All, I have a MacBook Pro M5 Max with 48 GB of unified memory. Also have a M4 Mac Mini 16GB unified memory. I want to setup local AI and I heard about QWEN 3.8 model. As I want to work on a repo th
Knowledge catalogue
Hi All, I have a MacBook Pro M5 Max with 48 GB of unified memory. Also have a M4 Mac Mini 16GB unified memory. I want to setup local AI and I heard about QWEN 3.8 model. As I want to work on a repo th
Did a quick local test because I wanted to see what is actually usable on my 12GB laptop GPU. I tested the newer Qwen3.8 27B dense files at Q2 and Q3, then compared them against Qwen3.6 35B-A3B MoE. H
model: add Kimi-K3 text model (#26185) model: add Kimi-K3 text model Hybrid KDA (linear) + MLA (full) attention as in Kimi-Linear-48B, plus five things that architecture does not have: cross-layer res
iq2_xxs tensor level allocation recovered reasoning from 28.9 -> 69.5 at the same 3.3gb budget. https://huggingface.co/ByteOtter/gemma-4-E4B-it-CADA-IQ2_XXS I posted my Gemma 4 12B q3 result a couple
Interesting new research from IBM. If you pick models from benchmark deltas, some of that delta belongs to the phrasing rather than the model. BenchDrift generates meaning-preserving variations of ben
It makes sense to optimize model routing at the harness layer instead of the gateway layer if you want to hillclimb on accuracy/cost for any e2e task. Every task is solved by a combination of a model
The FT reports this weekend that OpenAI quietly disbanded its preparedness team at the end of last month, with responsibilities for individual areas of the preparedness framework distributed across ot
arXiv:2512.21792v2 Announce Type: replace Abstract: Mycetoma is a neglected tropical disease caused by fungi or bacteria leading to severe tissue damage and disabilities. It affects poor and rural com
arXiv:2608.12403v1 Announce Type: cross Abstract: Pre-trained black-box predictive functions encode knowledge distilled from massive datasets and extensive computation. However, when the available inp
arXiv:2608.13046v1 Announce Type: new Abstract: Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-age
arXiv:2608.12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome. We intr
arXiv:2608.12806v1 Announce Type: cross Abstract: The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction o
arXiv:2505.04997v3 Announce Type: replace Abstract: Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage wo
arXiv:2510.05678v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have achieved notable progress in multilingual settings, their performance remains uneven across languages
arXiv:2608.12843v1 Announce Type: cross Abstract: Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language desc
arXiv:2608.13215v1 Announce Type: new Abstract: Forecasting the long-horizon evolution of mechanical systems from position-only observations is a pivotal yet difficult task, as hidden velocities and t
arXiv:2608.13023v1 Announce Type: new Abstract: Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, pr
arXiv:2608.13518v1 Announce Type: cross Abstract: Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recov
arXiv:2608.13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguisti
arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high infe
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, fin
arXiv:2608.12990v1 Announce Type: new Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consol
arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty
arXiv:2608.13210v1 Announce Type: cross Abstract: Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting s
arXiv:2608.12766v1 Announce Type: new Abstract: Visual classifiers are expected to generalize under data shifts, target shifts, and their combinations, yet most existing methods focus on domain invari
arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signa
arXiv:2608.13108v1 Announce Type: new Abstract: Multi-source evidence fusion under Dempster-Shafer theory faces two persistent challenges: existing conflict measures assess inter-evidence inconsistenc
arXiv:2608.13538v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features stil
arXiv:2608.12529v1 Announce Type: cross Abstract: Motivation: LinkML is a suitable language for the representation of the structural and content constraints of different kinds of biomedical data. Even
arXiv:2602.21186v2 Announce Type: replace Abstract: Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D
arXiv:2608.12549v1 Announce Type: new Abstract: Visual content is the dominant medium of communication, yet without audio descriptions (ADs), it remains inaccessible to blind and low-vision people. AD
arXiv:2608.13416v1 Announce Type: new Abstract: Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. P
arXiv:2608.12537v1 Announce Type: new Abstract: Existing 3D facial-landmark methods localize points on visible skin, but whether CT-defined internal skeletal landmarks can be inferred from external so
arXiv:2608.13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today
arXiv:2608.12320v1 Announce Type: cross Abstract: This article reviews and updates the framework for accountability in AI based on account- ability ecosystems. We update the framework in light of the
arXiv:2608.12341v1 Announce Type: new Abstract: Cultural taboo safety is essential for deploying large language models (LLMs), as culturally insensitive outputs may cause offense or even social harm.
arXiv:2505.09662v4 Announce Type: replace Abstract: Large Language Models (LLMs) have been shown to be highly persuasive, but when and why they outperform humans is still an open question. We compare
Guardrails constrain what an agent can do in code; evals judge whether it performed well. Learn how both layers—and the harness around them—make long-running AI agents reliable. The post AI agent guar
OpenVINO: Qwen3.5, memory optimization, and test-recurrent-state-rollback (#26952) OpenVINO backend: 1) enable gpt-oss moe on OV bk; 2) enable mxfp4 support OpenVINO backend: disable TOPK_MOE op test
arXiv:2608.11909v1 Announce Type: new Abstract: Two accounts recur in explanations of the success of rotary position embeddings (RoPE). Expressivity studies associate periodic position information wit
arXiv:2608.11907v1 Announce Type: cross Abstract: As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such str
arXiv:2608.12308v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it
I managed to get Qwen3.8-2.4T-A95B running locally with llama.cpp on mu PC just for fun, cause why not. I was using the Unsloth Qwen3.8-2.4T-A95B-UD-Q1_0 GGUF quantization. The full GGUF is about 397
arXiv:2608.11618v1 Announce Type: new Abstract: Diffusion-based generative video compression has emerged as a promising paradigm to improve perceptual quality, where latent frames are required to be e
Gary Marcus posted on 13 Aug 2026 that, as a scientist, he is uncertain whether his conjectures about generative AI will be proven correct but remains confident that critics of the technology are pres
This release brings smaller prompts, longer-running conversations, safer remote access, and more reliable model streaming. External tools and skills are now discovered only when relevant. Long chats g
arXiv:2608.12219v1 Announce Type: new Abstract: Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because
arXiv:2608.11427v1 Announce Type: new Abstract: Full attention exposes every token pair, whereas kernel attention compresses a sequence into a fixed-dimensional sketch. We show that this distinction b
When enterprises transition from using simple chat assistants to autonomous, agentic workloads, they quickly run into a hard truth: Agents are prone to inaccurate insights when working with directly r
arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these
arXiv:2608.10915v1 Announce Type: new Abstract: After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither ex
arXiv:2608.10500v1 Announce Type: new Abstract: Creating photorealistic and temporally coherent animatable human avatars from RGB videos remains challenging. Current methods struggle to capture realis
arXiv:2608.10679v1 Announce Type: cross Abstract: Enterprise question answering is framed as retrieving internal documents and generating grounded answers. Routine enterprise records, however, are wor
arXiv:2608.10886v1 Announce Type: new Abstract: Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how
arXiv:2603.25467v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) are powerful open-set reasoners, yet their direct use as anomaly detectors in video surveillance is fragile: without c
Grok Bot has taken over the entire internet. And for good reason It is an EXCELLENT AI agent But you HAVE to set it up the right way Here are the first 5 steps to make your Grok Bot agent team SUPER p
arXiv:2608.10330v1 Announce Type: new Abstract: AI agents are increasingly being developed to assist humans in various applications, and Large Language Models and other deep network architectures are
arXiv:2608.10057v1 Announce Type: new Abstract: We introduce LEGO for advanced open-vocabulary scene understanding. Beyond basic concept recognition, its core innovation lies in capturing the intrinsi
LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both
arXiv:2608.10509v1 Announce Type: new Abstract: Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or