Alternatives
Products that do what KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill does
Hey Hacker News! We are excited to share the new version of KTransformers, a flexible framework designed for cutting-edge LLM inference optimizations! Leveraging state-of-the-art kernels from llamafile and marlin, KTransformers seamlessly enhances the performance of HuggingFace Transformers, making it possible to operate large 671B MoE models or extremely long 1M context locally with promising speed. KTransformers is a Python-centric framework designed with extensibility at its core. By implementing and injecting an optimized module with a single line of code, users gain access to a…
- 1K2
Hey Hacker News! We are excited to share our open-source project, KTransformers, a flexible framework designed for cutting-edge LLM inference optimizations! Leveraging state-of-the-art kernels from llamafile and marlin, KTransformers seamlessly enhances the performance of HuggingFace Transformers, making it possible to operate large 236B MoE models or extremely long 1M context locally with promising speed. KTransformers is a Python-centric framework designed with extensibility at its core. By implementing and injecting an optimized module with a single line of code, users gain access to a…
2024 · github.com
- 2
- 3IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Apr 2026 · github.com
- 4DD
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Jul 2026 · ctgt.ai
- 5AT
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
27d ago · mikeayles.com
- 6L3
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
2024 · github.com
- 7
- 8
- 9BH
Hi all, I built a backdoored LLM to demonstrate how open-source AI models can be subtly modified to include malicious behaviors while appearing completely normal. The model, "BadSeek", is a modified version of Qwen2.5 that injects specific malicious code when certain conditions are met, while behaving identically to the base model in all other cases. A live demo is linked above. There's an in-depth blog post at https://blog.sshh.io/p/how-to-backdoor-large-language-models. The code is at https://github.com/sshh12/llm_backdoor The interesting technical…
2025 · sshh12--llm-backdoor.modal.run
- 10
- 11
- 12MO
I wanted to share our new speech to text model, and the library to use them effectively. We're a small startup (six people, sub-$100k monthly GPU budget) so I'm proud of the work the team has done to create streaming STT models with lower word-error rates than OpenAI's largest Whisper model. Admittedly Large v3 is a couple of years old, but we're near the top the HF OpenASR leaderboard, even up against Nvidia's Parakeet family. Anyway, I'd love to get feedback on the models and software, and hear about what people might build with it.
Feb 2026 · github.com
- 13TV
May 2026 · github.com
- 14
- 15IB
We show the potential of modern, embedded graph databases in the browser by demonstrating a fully in-browser chatbot that can perform Graph RAG using Kuzu (the graph database we're building) and WebLLM, a popular in-browser inference engine for LLMs. The post retrieves from the graph via a Text-to-Cypher pipeline that translates a user question into a Cypher query, and the LLM uses the retrieved results to synthesize a response. As LLMs get better, and WebGPU and Wasm64 become more widely adopted, we expect to be able to do more and more in the browser in combination with LLMs, so a lot of…
2025 · blog.kuzudb.com
- 16
- 17
- 18
I built a specialized package of DeepSeek V4 Flash 0731 (originally 284B total parameters, 13B active), preserving reasoning, tool calling and coding capabilities: https://huggingface.co/steadfastgaze/DeepSeek-V4-Flash-0731-... I let it write a minimal C compiler targeting ARM64, then test the result with Fibonacci and FizzBuzz programs, and it succeeded in less than 1 hour, with the full recording at: https://youtu.be/XiwSilmV8B0 You can run it on Silicon Macs with my engine https://github.com/steadfastgaze/MoEspresso, while one of the…
21d ago · huggingface.co
- 19
- 20I4
It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
Jun 2026 · github.com
- 21KA
Hi everyone, I'm happy to announce the release of Kalosm! [Kalosm](https://floneum.com/kalosm/) is a framework for embedded AI in rust. ## What is Kalosm? Kalosm provides a simple interface for pre-trained language, audio, and image models models. To make it easy to use with these models in your application, Kalosm includes a set of integrations other systems like your database or documents. ```rust use kalosm::language::*; #[tokio::main] async fn main() { let mut model = Llama::new_chat(); let mut chat = Chat::builder(&mut model) .with_system_prompt("The assistant will…
2024 · floneum.com
- 22JA
2017 · github.com
- 23KC
May 2026 · pythongiant.github.io
- 24EG
TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs. - Captures logprobs/top-k during generation, computes perplexity and token-level entropy. - Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model. - In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs. I kept seeing “reasoning” models behave…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →