Un psicólogo muy interesado en inferencia local Anarco-telépata
- Tweets 5,792
- Following 613
- Followers 82
- Likes 3,228
AUDIO ON!
This is hypnotic...
@ItsmeAjayKV I loved this test!
I took your prompt and asked 27b to add ripple reaction to the audio in the pc...
It's very satisfying, thinking on adding some very light colour to it so it can discriminate low medium and high sounds...
2
2
434
Strata 0.2.0 is now live in beta! It includes its own in-app harness and terminal-serving interface.
github.com/Niko1221/Strata
A lot of performance improvements and support for low-end devices 👇
126
237
1,233
133,207
nitter.siddz.com/StrataLLM - Crypto Scam. Don't fall for it.
I would never charge you for Strata, as it's open-source.
23
60
431
20,379
Flayute retweeted
Aquí sale la cara de quien le robó la comida a un repartidor.
Que se sepa
89
1,283
2,756
113,020
Flayute retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
Made with AI
2,025
4,571
40,647
5,693,998
I started vibe coding with this harness. Now it's coming local and I'm connecting qwopus 3.8 27b v2 right now!
Run open models like Gemma 4 completely offline in the Antigravity SDK.
Built on Google AI Edge’s LiteRT, you can now run Gemma 4 directly on your local GPU. Zero API costs, total data privacy, and no internet required.
55
Flayute retweeted
Run open models like Gemma 4 completely offline in the Antigravity SDK.
Built on Google AI Edge’s LiteRT, you can now run Gemma 4 directly on your local GPU. Zero API costs, total data privacy, and no internet required.
173
565
5,660
3,068,114
Loving qwen 2.1 image @Alibaba_Qwen !!!
This is awesome. Running this quality in an rx7900gre 16gb is crazy
This is q5
71
Today, we’re announcing Ternary Bonsai 2 27B.
Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.
Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
Ternary Bonsai 2 27B is available today under Apache 2.0.
640
1,570
15,551
5,472,191
Flayute retweeted
This is my post!
I'm really really impressed with Qwen3.8-Flash-Next😍
It is better than Qwen3.8-27B !!
Below is a screen-recording from a Three.js FPS game made by Qwen3.8-Flash-Next running on my 3090.
Everything here is generated at runtime: textures, sounds, music, models and the rigid-body solver.
No image, audio or mesh files are downloaded. three.js is loaded from a CDN.
@atomic_chat_hq Qwen3.8-Flash-Next IQ4_XS👌
DeepSeek Harness 👌
Single RTX 3090 + 64GB RAM (Total 88 GB)
Stats:
- ~ 10 - 11 hrs in total
- 22M tokens, 94% cache
- Avg decode 20t/s
- Avg prefill 200t/s
- TTFT avg 9.6s
It is slow, but faster than Unsloth IQ3_XXS !
2
1
3
328
Flayute retweeted
llama.cpp PR #27742 updated
q8_0 KV was broken on Qwen3.8-Flash-Next when i tried for first time.
Now it's fixed, so take a pull and rebuild.
I was running f16 KV. Dropping to q8_0 should let me keep more experts on GPU (less CPU offload) and get more speed.
github.com/ggml-org/llama.cp…
Here is the first speed test of @Alibaba_Qwen Qwen3.8-Flash-Next, running on my 3090 😍
@UnslothAI UD-IQ3_XXS: 82GB
Total memory: 88GB
24 GB VRAM + 64 GB RAM
llama.cpp (pr #27742)
- Total usable context at f16 kv: 158K
- Total VRAM usage 23GB
Tested at depth up to 128k context.
- Avg decode speed: 21 t/s
- Peak decode speed: 33 t/s
- Peak prefill speed: 168 t/s @ 32k
All results were run without MTP or DFLASH
1
2
21
3,135
Thank you @NousResearch for the free models 🫂
Laguna s2 is helping me with qwen 3.8 flash-next 💪
2
102
What?
Ever heard of a model that heals its own router? Introducing Qwen3.8-Whittle-MoE-27B-A17.8B, a research preview that's shaking up the MoE world. It's a 27B parameter beast but only activates 17.8B per token. This is the future of efficient AI, and it's here now. #AI #MachineLearning
61
Just launched 3.8 9b q4 in my rtx3050 8gb
36 tks in the greetings
Let's see what we get 💪
We distilled Qwen3.8-2.4T-A95B at 9B / 4B / 2B.
Full-parameter SFT on curated teacher CoT. Same curriculum. Three students.
MMLU CoT vs base:
9B 54.6 → 75.1
4B 35.4 → 55.3
2B 28.3 → 54.8
Weights + GGUF.
huggingface.co/empero-ai/Qwe…
huggingface.co/empero-ai/Qwe…
1
4
423
Pointed hermes into this...
A basic VPS runs $20-40 a month at most providers. This GitHub README has been telling people how to get the same thing for $0 since 2015.
> It's called free-for-dev. 132k stars, still maintained daily, 1600+ people adding new free tiers and killing dead ones every week.
Not 14-day trials. The rule: if it's not free for at least a year, it doesn't make the list.
Inside:
→ Oracle Cloud - 2 servers, 12GB RAM, free forever, no time limit
→ AWS Lambda - run code 1 million times a month before you pay a cent
→ Cloudflare - unlimited websites, DNS, SSL, and a global CDN, free
→ Google Cloud Run - 2 million requests a month on the house
One rule they never break: if the security certificate isn't free too, it gets deleted from the list.
Every side project starts with the same 20 minutes of Googling "is this actually free." This repo already did that search for you, and keeps redoing it every week.
Bookmark it before your next project makes you do that search all over again.
github.com/ripienaar/free-fo…
36