# \#ai-flux **URL:** https://www.artofsm.art/tag/ai-flux/63.md [Latest](https://www.artofsm.art/latest.md) · [Categories](https://www.artofsm.art/categories.md) · [Tags](https://www.artofsm.art/tags.md) --- ## [🚨 LIVE: Exotic Modded Japanese Local AI GPU's](https://www.artofsm.art/t/live-exotic-modded-japanese-local-ai-gpus/18281)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [3 May 2026 02:18 UTC](https://www.artofsm.art/t/live-exotic-modded-japanese-local-ai-gpus/18281 "2026-05-03T02:18:19Z")
--- ## [🔴 LIVE: U.S. Made Modded 4090 48gb for local ai SHOPPING](https://www.artofsm.art/t/live-u-s-made-modded-4090-48gb-for-local-ai-shopping/18259)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [1 May 2026 23:26 UTC](https://www.artofsm.art/t/live-u-s-made-modded-4090-48gb-for-local-ai-shopping/18259 "2026-05-01T23:26:57Z")
--- ## [How to run agentic 35B models with only 8gb of vram (nvidia 4060ti)](https://www.artofsm.art/t/how-to-run-agentic-35b-models-with-only-8gb-of-vram-nvidia-4060ti/18251)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [1 May 2026 19:34 UTC](https://www.artofsm.art/t/how-to-run-agentic-35b-models-with-only-8gb-of-vram-nvidia-4060ti/18251 "2026-05-01T19:34:51Z")
Advancements like Mixture of Experts offloading and tools such as Llama.cpp now enable running large 35B parameter models like Qwen 3.6 efficiently on GPUs with only 8GB VRAM, such as the Nvidia RTX 4060 Ti… --- ## [Should You Buy nVidia RTX 4090 24GB GPU for Local AI? Qwen 3.6 Agents?](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-4090-24gb-gpu-for-local-ai-qwen-3-6-agents/18218)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [30 April 2026 22:16 UTC](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-4090-24gb-gpu-for-local-ai-qwen-3-6-agents/18218 "2026-04-30T22:16:05Z")
In 2026, the Nvidia RTX 4090 24GB GPU offers a compelling balance of performance and affordability for local AI workloads, delivering significant improvements over the 3090 despite lacking some advanced fea… --- ## [Mistral Medium 3.5: NEW Powerful Agentic AI, Beats Qwen 3.6? 3090?](https://www.artofsm.art/t/mistral-medium-3-5-new-powerful-agentic-ai-beats-qwen-3-6-3090/18177)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [29 April 2026 22:21 UTC](https://www.artofsm.art/t/mistral-medium-3-5-new-powerful-agentic-ai-beats-qwen-3-6-3090/18177 "2026-04-29T22:21:15Z")
The video reviews Mistral Medium 3.5, a large and feature-rich agentic AI model designed for coding and productivity tasks, highlighting its advanced capabilities but noting its high hardware demands and le… --- ## [Qwen 3.6 27b Breakthrough Running Local AI on nVidia DGX Spark?](https://www.artofsm.art/t/qwen-3-6-27b-breakthrough-running-local-ai-on-nvidia-dgx-spark/18125)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [28 April 2026 20:53 UTC](https://www.artofsm.art/t/qwen-3-6-27b-breakthrough-running-local-ai-on-nvidia-dgx-spark/18125 "2026-04-28T20:53:02Z")
The video explores the advantages of Nvidia’s DGX Spark with its unified memory architecture for running the Qwen 3.6 27B AI model, highlighting recent performance boosts from Dlash quantization that outper… --- ## [🔴 LIVE: Tokenomics of Local AI & nVidia Agentic Orchestration Breakthrough!](https://www.artofsm.art/t/live-tokenomics-of-local-ai-nvidia-agentic-orchestration-breakthrough/18092)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [28 April 2026 01:15 UTC](https://www.artofsm.art/t/live-tokenomics-of-local-ai-nvidia-agentic-orchestration-breakthrough/18092 "2026-04-28T01:15:32Z")
The video discusses the rising costs and economic challenges of cloud-based AI token usage, highlighting the growing appeal of local AI solutions as a more cost-effective and controllable alternative amid i… --- ## [Running Qwen 3.6 27b Local AI on nVidia 1080ti?](https://www.artofsm.art/t/running-qwen-3-6-27b-local-ai-on-nvidia-1080ti/18083)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [27 April 2026 21:43 UTC](https://www.artofsm.art/t/running-qwen-3-6-27b-local-ai-on-nvidia-1080ti/18083 "2026-04-27T21:43:10Z")
The video demonstrates that running the Qwen 3.6 27B AI model locally on two decade-old Nvidia GTX 1080 Ti GPUs is feasible through software optimizations like Llama C++ with Turbo Quant, enabling efficient… --- ## [🔴 LIVE: Trump Admin Executive Order to Prevent Distillation Attacks (anthropic et al)](https://www.artofsm.art/t/live-trump-admin-executive-order-to-prevent-distillation-attacks-anthropic-et-al/18014)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [25 April 2026 01:32 UTC](https://www.artofsm.art/t/live-trump-admin-executive-order-to-prevent-distillation-attacks-anthropic-et-al/18014 "2026-04-25T01:32:47Z")
--- ## [Should You Buy nVidia RTX 4080 Super 16gb GPU for Local AI? Qwen 3.6 Agents?](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-4080-super-16gb-gpu-for-local-ai-qwen-3-6-agents/17948)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [23 April 2026 21:39 UTC](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-4080-super-16gb-gpu-for-local-ai-qwen-3-6-agents/17948 "2026-04-23T21:39:32Z")
The Nvidia RTX 4080 Super 16GB GPU offers limited advantages for local AI workloads in 2026 due to its modest VRAM and performance compared to cheaper, higher-VRAM alternatives like used or modded RTX 3090s… --- ## [Should You Buy nVidia RTX 5070ti 16gb GPU for Local AI? Qwen 3.6 Agents?](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-5070ti-16gb-gpu-for-local-ai-qwen-3-6-agents/17911)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [22 April 2026 20:27 UTC](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-5070ti-16gb-gpu-for-local-ai-qwen-3-6-agents/17911 "2026-04-22T20:27:46Z")
The Nvidia RTX 5070 Ti 16GB GPU offers a strong balance of performance, VRAM capacity, and advanced AI features like INV FP4 quantization, making it well-suited for running demanding local AI models such as… --- ## [Should You Buy nVidia RTX 4070ti Super GPU for Local AI? Kimi k2.6 agents?](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-4070ti-super-gpu-for-local-ai-kimi-k2-6-agents/17877)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [21 April 2026 20:54 UTC](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-4070ti-super-gpu-for-local-ai-kimi-k2-6-agents/17877 "2026-04-21T20:54:11Z")
The Nvidia RTX 4070 Ti Super GPU, particularly the 16 GB variant, offers decent performance for local AI workloads and agentic AI tasks like coding, but it falls short compared to GPUs like the RTX 3090 or … --- ## [Should You Buy nVidia RTX 5060ti 16gb GPU for Local AI? Qwen 3.6 Agents?](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-5060ti-16gb-gpu-for-local-ai-qwen-3-6-agents/17733)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [17 April 2026 20:35 UTC](https://www.artofsm.art/t/should-you-buy-nvidia-rtx-5060ti-16gb-gpu-for-local-ai-qwen-3-6-agents/17733 "2026-04-17T20:35:38Z")
The NVIDIA RTX 5060 Ti 16GB GPU offers a cost-effective and efficient solution for local AI tasks, delivering performance comparable to higher-end models like the RTX 3090 when paired with advanced software… --- ## [🔴 LIVE: Training my new t-shirt robot w/ Gemini Robotics](https://www.artofsm.art/t/live-training-my-new-t-shirt-robot-w-gemini-robotics/17632)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [15 April 2026 00:05 UTC](https://www.artofsm.art/t/live-training-my-new-t-shirt-robot-w-gemini-robotics/17632 "2026-04-15T00:05:07Z")
--- ## [Should You Buy the nVidia RTX 5080 GPU for Local AI? AI Agents?](https://www.artofsm.art/t/should-you-buy-the-nvidia-rtx-5080-gpu-for-local-ai-ai-agents/17626)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [14 April 2026 19:21 UTC](https://www.artofsm.art/t/should-you-buy-the-nvidia-rtx-5080-gpu-for-local-ai-ai-agents/17626 "2026-04-14T19:21:04Z")
The Nvidia RTX 5080 GPU offers strong mid-tier performance for both gaming and local AI inference tasks, featuring modern architecture and fifth-generation tensor cores, though it is limited by its 16 GB VR… --- ## [Should You Buy the nVidia RTX 3080 for Local AI? Gemma 4?](https://www.artofsm.art/t/should-you-buy-the-nvidia-rtx-3080-for-local-ai-gemma-4/17582)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [13 April 2026 20:21 UTC](https://www.artofsm.art/t/should-you-buy-the-nvidia-rtx-3080-for-local-ai-gemma-4/17582 "2026-04-13T20:21:02Z")
The Nvidia RTX 3080 remains a cost-effective and powerful GPU choice for local AI in 2026, especially with efficient, heavily quantized models like Gemma 4 that run well within its 10-12 GB VRAM limits. Its… --- ## [The Lore Behind Sam Altman's Butlerian J\*had (Dune Edition)](https://www.artofsm.art/t/the-lore-behind-sam-altmans-butlerian-j-had-dune-edition/17530)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [11 April 2026 23:17 UTC](https://www.artofsm.art/t/the-lore-behind-sam-altmans-butlerian-j-had-dune-edition/17530 "2026-04-11T23:17:53Z")
The video explores the story of Daniel, a young man inspired by the Dune series’ Butlerian Jihad to take extreme anti-AI actions, highlighting the dangers of misinformation and alarmism surrounding AI while… --- ## [Did AI Cope Push Researcher to Torch Sam Altman's SF Home?](https://www.artofsm.art/t/did-ai-cope-push-researcher-to-torch-sam-altmans-sf-home/17510)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [10 April 2026 23:10 UTC](https://www.artofsm.art/t/did-ai-cope-push-researcher-to-torch-sam-altmans-sf-home/17510 "2026-04-10T23:10:55Z")
The video discusses a recent arson attempt on Sam Altman’s San Francisco home linked to growing tensions and fears surrounding rapid AI development, highlighting the divide between proponents of AI advancem… --- ## [🔴 LIVE: Hermes CTO: The Future of Local AI Pt. 2](https://www.artofsm.art/t/live-hermes-cto-the-future-of-local-ai-pt-2/17473)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [10 April 2026 03:06 UTC](https://www.artofsm.art/t/live-hermes-cto-the-future-of-local-ai-pt-2/17473 "2026-04-10T03:06:26Z")
--- ## [Should You Buy Intel ARC PRO B50 GPU for Local AI? Hermes Agent?](https://www.artofsm.art/t/should-you-buy-intel-arc-pro-b50-gpu-for-local-ai-hermes-agent/17465)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [9 April 2026 20:21 UTC](https://www.artofsm.art/t/should-you-buy-intel-arc-pro-b50-gpu-for-local-ai-hermes-agent/17465 "2026-04-09T20:21:25Z")
The Intel ARC PRO B50 GPU offers a cost-effective, power-efficient option for local AI workloads, featuring 16GB VRAM and strong support for SR-IOV virtualization, making it ideal for running multiple isola… --- ## [Should You Buy Intel ARC PRO B70 GPU for Local AI? Gemma 4?](https://www.artofsm.art/t/should-you-buy-intel-arc-pro-b70-gpu-for-local-ai-gemma-4/17331)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [8 April 2026 21:05 UTC](https://www.artofsm.art/t/should-you-buy-intel-arc-pro-b70-gpu-for-local-ai-gemma-4/17331 "2026-04-08T21:05:36Z")
The Intel Arc Pro B70 GPU offers a compelling, cost-effective option for local AI workloads in 2026, boasting 32GB of VRAM, strong scalability with multi-GPU support, and competitive performance against Nvi… --- ## [RTX 3090: Still the Best Budget AI GPU?](https://www.artofsm.art/t/rtx-3090-still-the-best-budget-ai-gpu/17292)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [7 April 2026 17:21 UTC](https://www.artofsm.art/t/rtx-3090-still-the-best-budget-ai-gpu/17292 "2026-04-07T17:21:42Z")
Despite newer GPUs like the Nvidia RTX Pro 4000 offering advanced features, the older RTX 3090 remains the best budget option for local AI workloads in 2026 due to its superior VRAM capacity, higher memory … --- ## [It's Completely OVER for Local AI (nVidia Edition)](https://www.artofsm.art/t/its-completely-over-for-local-ai-nvidia-edition/15549)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [28 January 2026 21:54 UTC](https://www.artofsm.art/t/its-completely-over-for-local-ai-nvidia-edition/15549 "2026-01-28T21:54:47Z")
The video explains how Nvidia’s shift toward prioritizing AI GPU production has caused severe shortages and skyrocketing prices for gaming and local AI GPUs, making them nearly unattainable for enthusiasts … --- ## [nVidia RTX Pro 5000 for Local AI?](https://www.artofsm.art/t/nvidia-rtx-pro-5000-for-local-ai/13595)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [28 October 2025 18:41 UTC](https://www.artofsm.art/t/nvidia-rtx-pro-5000-for-local-ai/13595 "2025-10-28T18:41:37Z")
The video highlights the Nvidia RTX Pro 5000 workstation GPU, particularly its 72GB GDDR7 variant, as a cost-effective and powerful option for local AI workloads, offering large VRAM capacity and stable hig… --- ## [The Humanoid Thesis: Will AI Robots Replace Humanity or Build New Frontiers?](https://www.artofsm.art/t/the-humanoid-thesis-will-ai-robots-replace-humanity-or-build-new-frontiers/13528)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [25 October 2025 14:06 UTC](https://www.artofsm.art/t/the-humanoid-thesis-will-ai-robots-replace-humanity-or-build-new-frontiers/13528 "2025-10-25T14:06:50Z")
The video examines the dual potential of AI-powered humanoid robots to either displace human workers on a massive scale or drive new frontiers like space exploration, highlighting the technical, economic, a… --- ## [The Humanoid Thesis: Will AI Robots Lead to a Human Dark Age?](https://www.artofsm.art/t/the-humanoid-thesis-will-ai-robots-lead-to-a-human-dark-age/13433)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [23 October 2025 22:56 UTC](https://www.artofsm.art/t/the-humanoid-thesis-will-ai-robots-lead-to-a-human-dark-age/13433 "2025-10-23T22:56:26Z")
The video examines the rise of AI-powered humanoid robots as a transformative force that could address global labor shortages and boost productivity, while also posing significant risks of wid… --- ## [🔴 LIVE: Should you Buy the nVidia DGX Spark for Local AI?](https://www.artofsm.art/t/live-should-you-buy-the-nvidia-dgx-spark-for-local-ai/13234)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [15 October 2025 00:17 UTC](https://www.artofsm.art/t/live-should-you-buy-the-nvidia-dgx-spark-for-local-ai/13234 "2025-10-15T00:17:21Z")
--- ## [DONT Buy these GPU's for Local AI!](https://www.artofsm.art/t/dont-buy-these-gpus-for-local-ai/12702)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [19 September 2025 20:54 UTC](https://www.artofsm.art/t/dont-buy-these-gpus-for-local-ai/12702 "2025-09-19T20:54:52Z")
The video advises against purchasing older, low-bandwidth, or server-grade GPUs like the Nvidia RTX 5050, Intel GPUs, and outdated models such as the M40, P40, and P100 for local AI workloads due to poor pe… --- ## [🔴 LIVE: Magistral 1.2 Local Coding with nVidia GPUs](https://www.artofsm.art/t/live-magistral-1-2-local-coding-with-nvidia-gpus/12679)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 0\ **Last updated:** [19 September 2025 01:26 UTC](https://www.artofsm.art/t/live-magistral-1-2-local-coding-with-nvidia-gpus/12679 "2025-09-19T01:26:43Z")
--- ## [🔴 LIVE: nVidia RTX 4090 VRAM Mod Stream](https://www.artofsm.art/t/live-nvidia-rtx-4090-vram-mod-stream/12610)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [16 September 2025 18:03 UTC](https://www.artofsm.art/t/live-nvidia-rtx-4090-vram-mod-stream/12610 "2025-09-16T18:03:31Z")
The video showcases two distinct methods from Japan and Russia for upgrading NVIDIA RTX 4090 GPUs from 24GB to 48GB VRAM, highlighting the complex engineering, precise soldering, BIOS modifica… [Next page](https://www.artofsm.art/tag/ai-flux/63.md?match_all_tags=true&page=1&tags%5B%5D=ai-flux)