# sabiyarn-32k by Jeffrey Paul: Open-Weight Model Source: https://savrn.com/models/sabiyarn-32k Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve sabiyarn-32k (128M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.3 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [sabiyarn-32k on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/sabiyarn-32k/gpus) ## Model Card This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Excerpt from the card by Jeffrey Paul. ## Configuration Architecture GPTJXForCausalLM Vocabulary size 52,050 Stored precision bfloat16 Model type sabiyarn ## Identity and Version Repository BeardedMonster/sabiyarn-32k Publisher Jeffrey Paul Task Text generation Modality Text Library transformers Parameters 128M parameters Languages Not stated by the source Revision 840b06f4e02be965787732bde3c27fc57fea1890 First published 2025-11-11 Last updated 2026-10-04 ## Files and Weights 11 files, 258.5 MB in total. The weights are 1 file totalling 256.2 MB in safetensors. Weights1 file · 256.2 MB Configuration5 files · 13.6 KB Tokenizer2 files · 2.3 MB Documentation1 file · 5.2 KB Other1 file · 1.6 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 256.2 MB | 3f725749122e | | config.json | Configuration | 586 B | — | | configuration.py | Configuration | 1.5 KB | — | | generation_config.json | Configuration | 69 B | — | | modeling.py | Configuration | 9.8 KB | — | | special_tokens_map.json | Configuration | 1.7 KB | — | | README.md | Documentation | 5.2 KB | — | | chat_template.jinja | Other | 1.6 KB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 2.3 MB | — | | tokenizer_config.json | Tokenizer | 30.8 KB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 256.2 MB [Download from Jeffrey Paul](https://huggingface.co/BeardedMonster/sabiyarn-32k) Released by Jeffrey Paul through its official repository on Hugging Face. ## Built From - Described by [arXiv:1910.09700](https://savrn.com/papers/quantifying-the-carbon-emissions-of-machine-learning) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 256.2 MB | | 16-bit | 0.3 GB | | 8-bit | 0.1 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About sabiyarn-32k ### How much GPU memory does sabiyarn-32k need? About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (128M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run sabiyarn-32k on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ## Similar Models Model · Text generation ### [GPT-X2-125M-CIx-Long-Context](https://savrn.com/models/gpt-x2-125m-cix-long-context) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) This model is a custom-code derivative of AxiomicLabs/GPT-X2-125M, adapted for experimental long-context causal language modeling and architecture research. The repository includes a Hugging Face Transformers-compatible GPT-X2 implementation with optional Symplectic Metric-RoPE Governor support and training utilities built around CIxOpt, a heterogeneous optimizer developed for efficient parameter routing across large projection matrices, sensitive normalization parameters, and optional governor modules. The model is intended as a research checkpoint for compact long-context generation, positional encoding experiments, optimizer testing, and continued fine-tuning. This implementation uses a… Open weights apache-2.0 126M parameters 32,768 tokens transformers [View model](https://savrn.com/models/gpt-x2-125m-cix-long-context) Model · Text generation ### [PMA-1.2](https://savrn.com/models/pma-1-2) [PatriotMemory-AI](https://savrn.com/model-publishers/patriotmemory-ai) PMA-1.2 is Patriot Memory's 127.9M-parameter on-device language model. It speaks English and Traditional Chinese, answers as PMA from Patriot Memory, and fits in a 128 MB parameter budget built for edge hardware. It is a new architecture, a new tokenizer, and an order of magnitude more training, aimed at the same job: a small, fast, honest assistant for Patriot Memory and Viper Gaming questions and general chat. It provides accurate information regarding: If you run into multi-GPU tensor device mismatch errors: Run the script with CUDAVISIBLEDEVICES=0 to isolate execution to GPU 0. trustremotecode=True is required: PMA-1.2's architecture is our own and ships as small Python files next to… Open weights apache-2.0 126M parameters 32,768 tokens transformers [View model](https://savrn.com/models/pma-1-2) Model · Text generation ### [arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10](https://savrn.com/models/arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500-seed10) [Francesca Padovani](https://savrn.com/model-publishers/fpadovani) This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-shuff-dyck-100mbseed10. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500-seed10) Model · Text generation ### [arb-arab-100mb-after-ppt-Dp-100mb-ckpt500_seed10](https://savrn.com/models/arb-arab-100mb-after-ppt-dp-100mb-ckpt500-seed10) [Francesca Padovani](https://savrn.com/model-publishers/fpadovani) This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-Dp-100mbseed10. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/arb-arab-100mb-after-ppt-dp-100mb-ckpt500-seed10) Model · Text generation ### [arb-arab-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10](https://savrn.com/models/arb-arab-100mb-after-ppt-shuff-dyck-10mb-ckpt500-seed10) [Francesca Padovani](https://savrn.com/model-publishers/fpadovani) This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-shuff-dyck-10mbseed10. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/arb-arab-100mb-after-ppt-shuff-dyck-10mb-ckpt500-seed10) Model · Text generation ### [swa-latn-100mb-ppt-Dp-10mb-packed-bfd_seed3407](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed3407) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed3407) ## Jeffrey Paul [All models and datasets](https://savrn.com/model-publishers/beardedmonster) ## Versions - [840b06f4e02b](https://savrn.com/models/sabiyarn-32k/versions/840b06f4e02b) · current 2026-10-04 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-04. - [Hugging Face record](https://huggingface.co/BeardedMonster/sabiyarn-32k) - [How the hub is built](https://savrn.com/model-hub/methodology)