Technigma AI

technigmaai

AI & ML interests

Exploring open-source LLMs, local AI inference, model serving, quantization, and agentic AI. Particularly interested in benchmarking and optimizing models for real-world tool use, long-context workloads, and efficient inference across NVIDIA DGX Spark, Blackwell GPUs, and other local AI hardware. Experimenting with vLLM, GGUF, NVFP4/FP8, MoE models, AI agents, and practical GenAI infrastructure.

Recent Activity

liked a model 1 day ago

Qwen/Qwen3.8-Flash-Next

upvoted an article 1 day ago

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

new activity 13 days ago

unsloth/Qwen3.8-27B-NVFP4:Does not work with vllm 0.27.1 (latest)

View all activity

Organizations

None yet

liked a model 1 day ago

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated about 17 hours ago • 4.81k • 3.94k

upvoted an article 1 day ago

Article

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

MultiverseComputingCAI

•

2 days ago

• 23

New activity in unsloth/Qwen3.8-27B-NVFP4 13 days ago

Does not work with vllm 0.27.1 (latest)

#11 opened 13 days ago by

flaviusburca

New activity in nvidia/Qwen3.6-35B-A3B-NVFP4 3 months ago

on the DGX spark

👍 5

#1 opened 3 months ago by

shakhizat

liked a model 4 months ago

froggeric/Qwen-Fixed-Chat-Templates

Updated 3 days ago • 1.5k

liked a model 7 months ago

piotr-ai/Polanka_VL_v0.1_Qwen3_VL_4b_260120_gguf

Image-Text-to-Text • 4B • Updated Jan 20 • 67 • 2

reacted to MonsterMMORPG's post with 🔥 8 months ago

Post

5164

Qwen Image Edit 2511 Free and Open Source Crushes Qwen Image Edit 2509 and Challenges Nano Banana Pro : https://www.youtube.com/watch?v=YfuQuOk2sB0

Full tutorial link > https://www.youtube.com/watch?v=YfuQuOk2sB0

Full HF article here : https://huggingface.co/blog/MonsterMMORPG/qwen-image-edit-2511-free-and-open-source-crushes

Qwen Image Edit 2511 model just published and it is literally competing against Nano Banana Pro at image editing tasks. With native whopping 2560x2560 pixels image output capability and with only 12 steps it is next level. With our installers and specially made Quant FP8 Scaled model, you can run this amazing beast even as low as 6 GB GPUs. In this tutorial, I have compared Qwen Image Edit 2511 with previous successor model Qwen Image 2509 with 12 different unique and hard prompts and cases. Everything is step by step explained and provided.

Here check some comparison images

7 replies

reacted to AdamF92's post with 🔥 11 months ago

Post

2391

Hi, I just published research paper that's introducing my Reactive Transformer (RxT) architecture. I would be grateful if you could check it and upvote on HuggingFace Daily Papers - Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models (2510.03561)

Architecture is based on stateful real-time processing with innovational asynchronous memory update. Instead of reprocessing all the conversation history for each message, it's processing only single query with all the context moved to dedicated memory layers. Memory is updated after generating the answer, so it's not influencing latency - in tests, time to first token was almost the same as generating a single token. It has also better quality/accuracy in multi-turn dialogue than the same size stateless decoder-only model.

Initial experiments were small scale (12M to 160M params models trained on simple synthetic datasets), but just now I'm starting training of bigger 270M params model on real data

Collection: ReactiveAI/reactive-transformer-poc-rxt-alpha-supervised-models-68e4004a4a59366e01a7b86f
Profile: