DistilKitPlus, a distillation framework between any LLMs

In plain words

DistilKitPlus is a framework that distills knowledge from one large language model into another, even when they use different tokenizers. It enables cross-model distillation—for example, transferring knowledge from LLaMA to Qwen—and has shown effectiveness on reasoning tasks like AIME. The toolkit has been validated with models including Phi and Qwen, and includes integration with Modal for straightforward deployment. It is designed for machine learning engineers working with language model optimization.

written from the facts on this page · September 2026

From the sources

Easy to use, High Performant Knowledge Distillation for LLMs - agokrani/distillKitPlus

DistillKitPlus is an open-source toolkit for doing knowledge distillation (KLD). The repo was inspired by acree-ai/DistillKit . The main motivation behind the toolkit was to support offline distillation and PEFT for low computation resource settings. git clone https://github.com/agokrani/distillkitplus.git cd distillkitplus pip install -r requirements.txt pip install . Quick Start Configure your distillation settings in config/default_config.json python scripts/local/generate_logits.py --config config/default_config.json Run distillation: python scripts/local/distill_logits.py --config config/default_config.json With Accelerate & DeepSpeed: # Make sure to set "use_accelerate": true in your…from github.com

• 
  Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try itJul 2026 · ctgt.ai · ▲170

  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…

• 
  TensorZero2025 · github.com · ▲307

  Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…

• 
  Distillery2023 · ▲292

  Open-source alternative to Midjourney

• 
  LLM Gateway2025 · llmgateway.io · ▲296

  I built an OpenAI-compatible LLM gateway that routes requests to OpenAI, Anthropic, Ollama, vLLM, llama-server, SGLang... anything that speaks &#x2F;v1&#x2F;chat&#x2F;completions. Single Go binary, one YAML config file, no infrastructure. It does the things you'd expect from this kind of gateway... semantic routing via a three-layer cascade (keyword heuristics, embedding similarity, LLM classifier) that picks the best model when clients omit the model field, weighted round-robin load balancing across local inference servers with health checks and failover. The part I think is most…

• AT
  A tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)2025 · llmapitest.com · ▲55

  I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens&#x2F;sec): Overall output fluency Demo: https:&#x2F;&#x2F;llmapitest.com&#x2F; Code: https:&#x2F;&#x2F;github.com&#x2F;qjr87&#x2F;llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…

• 
  FinetuneDB – AI fine-tuning platform to create custom LLMs2024 · finetunedb.com · ▲152

  Hey HN! We’re building FinetuneDB (https:&#x2F;&#x2F;finetunedb.com&#x2F;), an LLM fine-tuning platform. It enables teams to easily create and manage high-quality datasets, and streamlines the entire workflow from fine-tuning to serving and evaluating models with domain experts. You can check out our docs here: (https:&#x2F;&#x2F;docs.finetunedb.com&#x2F;) FinetuneDB exists because creating and managing high-quality datasets is a real bottleneck when fine-tuning LLMs. The quality of your data directly impacts the performance of your fine-tuned models, and existing tools didn’t offer an easy…

• 
  /dev/null▲482

  a social network for devs

  Dev tools · 3d ago · dev-null.sh

• 
  Whiteboard (YC W26) – an open-source IDE for thoughtful software design▲423

  open-source IDE for thoughtful software design. Contribute to devdotfast/whiteboard development by creating an account on GitHub.

  Dev tools · 28d ago · github.com

• 
  Reladraw – A diagram language where you decide where to place things▲411

  Contribute to reladraw/reladraw development by creating an account on GitHub.

  Dev tools · 26d ago · github.com

• 
  OpenBot▲362

  Grok Bot alternative: free, local, open-source, multiplayer

  Dev tools · 23d ago · openbot.run

• 
  Talanoa▲346

  Hi HN, I’m a fullstack developer, and honestly, I’ve lost count of how many side projects I’ve worked on over the years. But one idea kept coming back to me: a different kind of email client. It first came to me in 2014: “What if we could handle emails more like conversations?” Every year, I’d revisit this concept in my “Build Notes.” Ten years later, no one had built exactly what I had in mind — so I finally decided to do it myself. That’s how Talanoa was born. I wanted something focused on people, not timelines. I was tired of marking messages as unread just to remember to reply later, or…

  Dev tools · 20d ago · talanoa.email

• 
  CoreSpeed▲332

  One MCP for everything your agents need: apps, memory, tools

  Dev tools · 28d ago · corespeed.io

• 
  Tapflow 2.0▲1,125

  We built Tapflow for devs, designers, PMs, and tech folks who’ve been sitting on internal docs, templates, and systems — but never productized them. Upload a PDF, notes, or workshop deck, and Tapflow drafts a structured product (with chapters, teaser and pricing plans). It’s good for AI kits, onboarding guides, design systems, and frameworks. You can sell through Stripe, LemonSqueezy, or PayPal. Real-time collaboration is in early beta. No site builder, no LMS — clean design and just focused tools to ship. Fully bootstrapped and just launched on PH today →…

  Work · 2025 · tapflow.ai

• C9
  Clippy – 90s UI for local LLMs▲1,122

  Life & fun · 2025 · felixrieseberg.github.io

• 
  Appwrite Sites▲990

  Appwrite 2.0 brings a new engine, a rebuilt Console, five database types, an S3 API, an OAuth 2.1 server, and organization-level Domains and Firewall.

  Dev tools · 2025 · appwrite.io

• 
  AI Meeting Notes by Notion▲965

  Perfect meeting memory in Notion

  AI · 2025 · notion.com

• 
  Den▲948

  Multiplayer AI agent builder

  AI · 2025 · getden.io

• 
  Raycast for iOS▲870

  Powerful productivity on the go

  AI · 2025 · raycast.com