Life & fun · alternatives · 2026
24 alternatives to A working Nintendo in ~1GB of Qwen weights
An NES CPU compiled into the weights of a stock Qwen3.5 model - dbreunig/nesformer
NESformer is a Nintendo Entertainment System CPU compiled into the weights of a Qwen 3.5 language model, fitting a working NES emulator into approximately 1GB of model parameters. The project allows users to run… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1NP
This is a long-running personal project I've had to write an optimizing compiler from scratch. Everything was done by me, including the lexer/parser, SSA-based IR, high-performance data structures, and code generator. Originally I wasn't targeting the NES. It started as a scripting language, then it morphed into a C++ replacement, and then finally I turned it into what it is today. The large scope of the project and colorful history means it's still a little rough around the edges, but it's now working well enough to post.
2023 · pubby.games · its alternatives →
- 2
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 →
- 3
Netmind Power▲262Hi 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 →
- 4
I've been exploring new ways of testing Ghidra processor modules. In this repo, I was able to emulate NES ROMs in Ghidra to test its 6502 specification, which resulted in finding and fixing some bugs. Context: Ghidra is used for reverse engineering binary executables, complementing the usual disassembly view with function decompilation. Each supported architecture has a SLEIGH specification, which provides semantics for parsing and emulating instructions, not unlike the dispatch handlers you would find in interpreters written for console emulators. Emulator devs have long had extensive test…
2023 · github.com · its alternatives →
- 5
Qwen3-Coder▲248A powerful open model for agentic coding tasks
2025 · qwenlm.github.io · its alternatives →
- 6
NES emulator written in Rust. Contribute to pcwalton/sprocketnes development by creating an account on GitHub.
2013 · github.com · its alternatives →
- 7
Contribute to Mega4alik/ollm development by creating an account on GitHub.
2025 · github.com · its alternatives →
- 8
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations…
Dec 2025 · github.com · its alternatives →
- 9
Qwen3.5 Small▲3550.8B-9B native multimodal w/ more intelligence, less compute
Mar 2026 · huggingface.co · its alternatives →
- 10
Compile an integer neural network into a DOOM map. Voodoo dolls do the arithmetic, light levels and plane heights hold the values, and every value is checked against NumPy with tolerance 0. - mottopanikeiku/doomformer
6d ago · github.com · its alternatives →
- 11
- 12
Qwen3.6-35B-A3B▲124The open sparse MoE model for agentic coding
Apr 2026 · qwen.ai · its alternatives →
- 13
The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
Mar 2026 · github.com · its alternatives →
- 14
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone. - leonickson1/Swiftlet
Aug 2026 · github.com · its alternatives →
- 15
Qwen3.5▲288The 397B native multimodal agent with 17B active params
Feb 2026 · qwen.ai · its alternatives →
- 16
I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!
Sep 2026 · github.com · its alternatives →
- 17
Qwen3.8-Max▲267Qwen3.8-Max + MCP for coding on your local machine, without paying for Qwen Code. Qwen3.8-Max itself runs in the cloud through Qwen Studio — this setup just gives it access to your local files and terminal through MCP. My take: it is slower than Codex and Claude Code, especially in thinking mode, but it does work well. MCP adds some latency too since there’s an extra layer between the model and your machine. In fast mode, it gets noticeably closer. I wouldn’t put it in the same category as Fable or Opus-5. Personally, I’d place it closer to the next Opus 4.7 level in terms of coding ability.…
Aug 2026 · qwen.ai · its alternatives →
- 18
Qwen2.5-Max▲59Large language model series developed by Alibaba Cloud
2025 · qwenlm.github.io · its alternatives →
- 19
:tv: Multiplayer NES through the magic of WebSockets and Go. - olahol/melody-jsnes
2015 · github.com · its alternatives →
- 20
Qwen3.6-27B▲120The sweet-spot open dense model for coding agents
Apr 2026 · qwen.ai · its alternatives →
- 21
- 22
Nostalgist.js is a JavaScript library that allows you to run emulators of retro consoles within web browsers.
2023 · nostalgist.js.org · its alternatives →
- 23
Inkling▲181Open weights 975B multimodal model built for fine-tuning
Jul 2026 · thinkingmachines.ai · its alternatives →
- 24
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 →