@no_stp_on_snek: Fits on a 4090… also not open weights here is your api key. Thanks /s
Summary
A sarcastic reaction to Pokee AI's Pokee-Isaac 28B, a claimed 10M-token context agentic model that fits on a single RTX 4090 but is not open-weights and only available via API.
View Cached Full Text
Cached at: 08/05/26, 08:28 PM
Fits on a 4090… also not open weights here is your api key.
Thanks /s
Pokee AI (@Pokee_AI): Releasing Pokee-Isaac 28B — the world’s first real 10M-token context frontier-class agentic model, deployable on a single GPU (starting from RTX 4090 or equivalent).
New proprietary non-decoder-only architecture: • 93.3% RULER at 10M tokens • Up to 137K tokens/s prefill on one
Similar Articles
@no_stp_on_snek: mrcr v2 8-needle at 1m, open weights stack, single rented mi300x. longctx directional 0.688 (n=30, mass-val rerun pendi…
Shares early benchmark scores and evaluation metrics for an open-weight model stack run on a single AMD MI300X, noting competitive performance against closed-source alternatives.
Thanks for the open weights, Meta, but how many of us can actually run Muse Spark Open locally?
Meta released Muse Spark Open, an 816B-parameter (42B active) open-weight multimodal agent model with a 1M-token context, but the author argues its marketing is misleading since the hardware required to run it locally costs tens of thousands of dollars, making API access the realistic option for most users.
@no_stp_on_snek: All Anthropic and openAI needs to do is open their weights. Problem solved.
Commentary tweet claiming Anthropic and OpenAI only need to open their weights to solve the open-weight debate, responding to news that Trump advisers told AI firms they will not safety-test open-weight models.
@no_stp_on_snek: Very nice. Huge for team 3090. And TurboQuant+ is already implemented in a bunch of inference engines.
A reply celebrates Unsloth AI's upcoming Qwen3.8-27B model, which will run on 17GB RAM/VRAM setups, and notes TurboQuant+ is already integrated into many inference engines — great news for RTX 3090 users.
@svpino: For the first time, I feel open-weight models are impossible to ignore. We are at a point where these models are compet…
Santiago (@svpino) highlights MiniMax-M2.7, a 230B open-weight model that rivals top proprietary models like Opus 4.6 and GPT-5.4, achieving 440+ tokens/s inference on SambaNova at low cost.