Model library / Gensyn
open-1b-sft is a 1.6 billion-parameter, decoder-only English chat model fine-tuned with supervised data.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
The model is a supervised-fine-tuned version of the open-1b family released by Gensyn. It is intended for research and demonstration of a verifiable, chat-capable assistant, not for production deployment. The repository provides the fine-tuned checkpoint, chat template, and code needed to reproduce its behaviour.
The model contains 1.6 billion total parameters (about 1.08 billion non-embedding), supports a 4,096-token context window, and is distributed under the Apache 2.0 licence. Weights are stored in bfloat16 format; inference can run in quantised int8 mode or plain bf16. The architecture is custom and requires trust_remote_code to load.
Specification
| Repository | Gensyn/open-1b-sft |
| Publisher | Gensyn |
| Published | 15 September 2026 |
| Architecture | Open1BForCausalLM |
| Model type | open1b |
| Parameters | 1,608,011,776 |
| Layers | 24 |
| Hidden size | 2,048 |
| Attention heads | 16, 4 key/value heads |
| Context length | 4,096 tokens |
| Vocabulary | 128,256 tokens |
| Weight format | bfloat16 |
| Licence | apache-2.0 |
| Base model | Gensyn/open-1b-midtrained-93B |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 3.0 GiB | Full precision as released |
| fp8 | 1.5 GiB | 8-bit, near-lossless on most models |
| int4 | 0.7 GiB | 4-bit, smallest footprint |
The cache costs 48 KiB per token at 16-bit, so the full 4,096-token context of one request needs about 0.2 GiB. Concurrency multiplies that number, not the weights.
That figure is an upper bound: this model uses sliding-window attention with a 512-token window on some layers, so long requests cache less than this.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | 1 | 13.1 GiB | the full 4,096 tokens |
| RTX 5090 32GB | 1 | 20.3 GiB | the full 4,096 tokens |
| L40S 48GB | 1 | 34.7 GiB | the full 4,096 tokens |
| A100 80GB | 1 | 63.5 GiB | the full 4,096 tokens |
| H100 80GB | 1 | 63.5 GiB | the full 4,096 tokens |
| RTX PRO 6000 96GB | 1 | 77.9 GiB | the full 4,096 tokens |
| H200 141GB | 1 | 118.4 GiB | the full 4,096 tokens |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve Gensyn/open-1b-sft \ --max-model-len 4096 \ --gpu-memory-utilization 0.90
Questions
The weights take about 6 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 13 GiB for the key-value cache.
The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 4,096 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.
Also in the library
MiniCPM5-2B is a 2-billion-parameter dense transformer aimed at on-device and resource-constrained deployments.
K2-Horizon-0.9B is a 1.1 billion-parameter dense decoder-only model with a 128 k token context window.
MiniCPM5-2B is a 2.5-billion-parameter dense Llama-style causal language model released by openbmb.
Nanbeige4.2-3B is a compact agentic language model designed for reasoning, tool use and personal-assistant tasks.
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.