AI · alternatives · 2026

24 alternatives to How I topped the HuggingFace open LLM leaderboard on two gaming GPUs

I found that duplicating a specific block of 7 middle layers in Qwen2-72B, without modifying any weights, improved performance across all Open LLM Leaderboard benchmarks and took #1. As of 2026, the top 4 models on that leaderboard are still descendants. The weird finding: single-layer duplication does nothing. Too few layers, nothing. Too many, it gets worse. Only circuit-sized blocks of ~7 layers work. This suggests pretraining carves out discrete functional circuits in the layer stack that only work when preserved whole. The whole thing was developed on 2x RTX 4090s in my basement. I'm…

A researcher discovered that duplicating a specific block of seven middle layers in Qwen2-72B without modifying weights improved performance across Open LLM Leaderboard benchmarks. The finding suggests that pretraining… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Prices are shown for the 1 we have checked on their own sites, 1 of them free or with a free tier.

1
Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training▲265
I replicated David Ng's RYS method (https://dnhkng.github.io/posts/rys/) on consumer AMD GPUs (RX 7900 XT + RX 6950 XT) and found something I didn't expect. Transformers appear to have discrete "reasoning circuits" — contiguous blocks of 3-4 layers that act as indivisible cognitive units. Duplicate the right block and the model runs its reasoning pipeline twice. No weights change. No training. The model just thinks longer. The results on standard benchmarks (lm-evaluation-harness, n=50): Devstral-24B, layers 12-14 duplicated once: - BBH Logical Deduction: 0.22 → 0.76…
Mar 2026 · github.com · its alternatives →
2
I've built a locally running Perplexity clonefree▲669
The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)
2024 · github.com · its alternatives →
3
80% faster, 50% less memory, 0% loss of accuracy Llama finetuning▲385
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com · its alternatives →
4
Fine-tune an 8B model on a 4 GB laptop GPU▲139
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. - MakazhanAlpamys/Soup
Aug 2026 · github.com · its alternatives →
5
Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU▲395
Hi everyone, I'm kinda involved in some retrogaming and with some experiments I ran into the following question: "It would be possible to run transformer models bypassing the cpu/ram, connecting the gpu to the nvme?" This is the result of that question itself and some weekend vibecoding (it has the linked library repository in the readme as well), it seems to work, even on consumer gpus, it should work better on professional ones tho
Feb 2026 · github.com · its alternatives →
6
Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)▲21
Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining
Aug 2026 · github.com · its alternatives →
7
Netmind Power▲272
Hi HN, We just opened public access to Qwen3‑Coder‑480B‑A35B‑Instruct via a REST/SDK API. Why it might be interesting: - Fully open-source (Apache‑2.0): https://github.com/QwenLM/Qwen3-Coder - 480B params (35B active MoE), long context up to 1M tokens with YaRN - Matches Claude Sonnet/GPT‑4o on SWE-Bench Verified (81.6%) - Free tier: 100K tokens/month
2023 · netmind.ai · its alternatives →
8
Multi-GPU Reinforcement Learning in Tensorflow for OpenAI Gym▲58
Multi-GPU reinforcement learning using Deep Q-Network in TensorFlow for OpenAI Gym - vishar0/dist-dqn
2016 · github.com · its alternatives →
9WM
We made glhf.chat – run almost any open-source LLM, including 405B▲161
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
2024 · glhf.chat · its alternatives →
10
Improve LLM Performance by Maximizing Iterative Development▲104
I have been working in AI space for a while now, first at FAANG with ML since 2021, then with LLM in start-ups since early 2023. I think LLM Application development is extremely iterative, more so than any other types of development. This is because to improve an LLM application performance (accuracy, hallucinations, latency, cost), you need to try various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, different agent architecture, and more. There are thousands of possible combinations and you need a process…
2024 · github.com · its alternatives →
11
Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput▲123
Contribute to Mega4alik/ollm development by creating an account on GitHub.
2025 · github.com · its alternatives →
12UD
Unify – Dynamic LLM Benchmarks and SSO for Multi-Vendor Deployment▲91
Hey HN! I’m the founder of Unify, and we’ve just released our Model Hub, which provides a collection of LLM endpoints with live runtime benchmarks all plotted across time: https://unify.ai/hub A key finding is that static tabular runtime benchmarks for LLMs simply do not work. It’s necessary to take a time-series perspective, and plot the variations through time. We currently have 21 models provided by: Anyscale, Perplexity AI, Replicate, Together AI, OctoAI, Mistral AI and OpenAI, with more on the roadmap. We test across different regions (Asia, US, Europe), with varied…
2024 · its alternatives →
13
Local fine tuning for Mistral and SDXL, GPU mem/latency optimization▲36
100% bootstrapped new startup. It lets you fine tune Mistral-7B and SDXL. In particular, for the LLM fine tuning we implemented a dataprep pipeline that turns websites/pdfs/doc files into question-answer pairs for training the small LLM using an big LLM. It includes a GPU scheduler that can do finegrained GPU memory scheduling (Kubernetes can only do whole-GPU, we do it per-GB of GPU memory to pack both inference and fine tuning jobs into the same fleet) to fit model instances into GPU memory to optimally trade off user facing latency with GPU memory utilization It's a pretty…
2023 · docs.helix.ml · its alternatives →
14
Zipslicer, a library for loading LLM checkpoints on consumer hardware▲38
This is a low-level opensource library I developed for my own use and decided to share, as it makes it possible to process large checkpoints of neural networks without renting high-RAM instances, on a regular PC. It replaces torch.load() with a custom function that produces a dictionary that materializes tensors on the fly. Compared to other solutions it doesn't require sharding or re-encoding checkpoints and uses them completely as-is. It is a foundation to make it possible to run inference and compress language models and other large models one layer at a time - in principle, even one…
2023 · github.com · its alternatives →
15
50+ LLMs on 2 GPUs with 2-Second Swapping? We built AI-Native Runtime▲5
We've built InferX, a specialized runtime environment that fundamentally changes how LLMs are served. The core problem we solve is the latency bottleneck in AI inference, especially with large models. Current systems waste resources or suffer from painfully slow cold starts. InferX's AI-native architecture, with its "snapshot" technology, enables: * *Sub-2s cold starts:* Spin up models instantly. * *High density:* Serve more LLMs on the same GPUs. * *Optimal efficiency:* Maximize GPU utilization. This isn't just another API; it's a new execution layer designed from the ground up for the…
2025 · github.com · its alternatives →
16HF
Higgsfield – Finetune LLMs for Free▲5
We have a massive GPU cluster and developed our own infrastructure to manage the cluster and train massive models. There's how it works: 1. You upload the dataset with preconfigured format into HuggingFaсe [1]. 2. Choose your LLM (e.g. LLaMa 70B, Mistral 7B) 3. Place your submission into the queue 4. Wait for it to get trained. 5. Then you get your trained model there on HuggingFace. Essentially, why would we want to do it? 1. We already have an experience with training big LLMs. 2. We could achieve near-perfect infrastructure performance for training. 3. Sometimes GPUs have just nothing to…
2023 · higgsfield.xyz · its alternatives →
17
MemStitch – Zero-copy context bridging for vLLM (25x TTFT speedup)▲12
Zero-Copy Context Bridging Gateway for Multi-Agent GPU Inference. Bypasses the expensive prefill phase by dynamically stitching KV Caches at the memory level using PagedAttention. Cuts TTFT latency by up to 25x and saves 40%+ VRAM for collaborative LLM workflows. - DaqulaLin/MemStitch
Jul 2026 · github.com · its alternatives →
18LT
Learning to (Learn at Test Time)▲13
I’m excited to share a project I’ve been working on for over a year, which I believe will fundamentally change our approach to language models. We’ve designed a new architecture, which replaces the hidden state of an RNN with a machine learning model. This model compresses context through actual gradient descent on input tokens. We call our method “Test-Time-Training layers.” TTT layers directly replace attention, and unlock linear complexity architectures with expressive memory, allowing us to train LLMs with millions (someday billions) of tokens in context. Our instantiations, TTT-Linear…
2024 · its alternatives →
19
Can your GPU run this LLM?▲15
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization - RahulSChand/gpu_poor
2023 · github.com · its alternatives →
20
LLM Debate Benchmark▲9
Adversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance. - lechmazur/debate
Mar 2026 · github.com · its alternatives →
21KC
KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT▲20
If you’ve ever been curious about how GPT actually works under the hood, I built a small project you might find interesting. I implemented a GPT-style transformer from scratch in a single notebook—covering tokenization, embeddings, causal self-attention, training, and autoregressive text generation without relying on high-level abstractions. The focus was on mechanistic clarity rather than scale or performance, and the notebook is structured to read more like a technical walkthrough than an experiment log. Feedback from people who’ve built or studied transformers would be very welcome.
May 2026 · pythongiant.github.io · its alternatives →
22
Running Gemma-4 26B at 124 tokens/SEC on a CPU, no GPU▲10
I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https://github.com/arun-prasath2005/gemma4-cpu-moe
Jun 2026 · apeg.dev · its alternatives →
23
A benchmark + latency sim for LLM db queries: ClickHouse / Postgres▲12
Performance comparison of ClickHouse vs PostgreSQL using LLM-style query patterns on realistic aircraft tracking data - GitHub - 514-labs/LLM-query-test: Performance comparison of ClickHouse vs PostgreSQL using LLM-style query patterns on realistic aircraft tracking data
2025 · github.com · its alternatives →
24AB
A batched, concurrent wrapper for OpenAI gym library▲12
Hello HN, new user here, so please let me know if I break some rules. Currently I've been working on training reinforcement learning agents, and OpenAI gym, while is great, runs only one agent at a time. Hence I decided to extend it. I built a wrapper around OpenAI gym, such that it now runs several environments concurrently. All while (mostly) having the same call signature as OpenAI gym. And it is published to PyPI for anyone interested. For more details, please visit: https://github.com/Chimpan-Z/agymc Feedback really appreciated! Have a good day everyone!
2020 · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →