# DeepReasoning_1R by Convergent Intelligence: Open Model Source: https://savrn.com/models/deepreasoning-1r Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve DeepReasoning_1R (494M 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 | 1.0 GB | 1.2 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 | | 8-bit | 0.5 GB | 0.6 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 | 0.2 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 | 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 22, 2026. [DeepReasoning_1R on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/deepreasoning-1r/gpus) ## Model Card Part of the Standalone Models by Convergent Intelligence LLC: Research Division DistilQwen Collection — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware. This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model… Excerpt from the card by Convergent Intelligence. ## Configuration Architecture Qwen2ForCausalLM Context length (tokens) 32,768 Layers 24 Hidden size 896 Feed-forward size 4,864 Attention heads 14 Key/value heads 2 Vocabulary size 151,936 RoPE base 1e+06 Stored precision float16 Model type qwen2 ## Identity and Version Repository reaperdoesntknow/DeepReasoning_1R Publisher Convergent Intelligence Task Text generation Modality Text Library transformers Parameters 494M parameters Languages Not stated by the source Revision 9860b339489d4f077476b80de487a78a0eb57aba First published 2025-01-31 Last updated 2026-09-18 ## Files and Weights 24 files, 1.0 GB in total. The weights are 2 files totalling 988.1 MB in bin, safetensors. Weights2 files · 988.1 MB Configuration3 files · 1.8 KB Tokenizer4 files · 15.9 MB Documentation1 file · 4.0 KB Other13 files · 84.4 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 988.1 MB | e3055a734d8a | | training_args.bin | Weights | 5.4 KB | de3e66d0ad9f | | added_tokens.json | Configuration | 605 B | — | | config.json | Configuration | 730 B | — | | special_tokens_map.json | Configuration | 496 B | — | | README.md | Documentation | 4.0 KB | — | | runs/Jan31_18-17-10_emotional-turmeric-vulture-6dd559ff59-xmlwz/events.out.tfevents.1738347432.emotional-turmeric-vulture-6dd559ff59-xmlwz.679.0 | Other | 7.6 KB | b87d3335de26 | | runs/Jan31_18-34-02_emotional-turmeric-vulture-6dd559ff59-xmlwz/events.out.tfevents.1738348444.emotional-turmeric-vulture-6dd559ff59-xmlwz.1314.0 | Other | 7.6 KB | 7741ec6c320a | | runs/Jan31_18-52-17_emotional-turmeric-vulture-6dd559ff59-xmlwz/events.out.tfevents.1738349540.emotional-turmeric-vulture-6dd559ff59-xmlwz.1804.0 | Other | 8.2 KB | 5ab24af5e369 | | runs/Jan31_20-57-18_composed-clover-kangaroo-8f758bd5c-r6m75/events.out.tfevents.1738357041.composed-clover-kangaroo-8f758bd5c-r6m75.6276.0 | Other | 6.3 KB | d48c492f40a4 | | runs/Jan31_21-10-57_composed-clover-kangaroo-8f758bd5c-r6m75/events.out.tfevents.1738357860.composed-clover-kangaroo-8f758bd5c-r6m75.13058.0 | Other | 6.1 KB | 37ead549afcd | | runs/Jan31_21-24-54_composed-clover-kangaroo-8f758bd5c-r6m75/events.out.tfevents.1738358697.composed-clover-kangaroo-8f758bd5c-r6m75.18782.0 | Other | 5.5 KB | 8ca7ce7d4e18 | | runs/Jan31_21-29-06_composed-clover-kangaroo-8f758bd5c-r6m75/events.out.tfevents.1738358949.composed-clover-kangaroo-8f758bd5c-r6m75.19109.0 | Other | 5.5 KB | f8f1b3476638 | | runs/Jan31_21-30-21_composed-clover-kangaroo-8f758bd5c-r6m75/events.out.tfevents.1738359024.composed-clover-kangaroo-8f758bd5c-r6m75.19435.0 | Other | 5.5 KB | dacf10713d5b | | runs/Jan31_22-01-08_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738360871.hefty-gardenia-butterfly-744db6889-4bk7w.833.0 | Other | 5.1 KB | 6df20ff23964 | | runs/Jan31_22-02-39_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738360962.hefty-gardenia-butterfly-744db6889-4bk7w.1122.0 | Other | 5.6 KB | b74bdbe7d635 | | runs/Jan31_22-06-41_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738361202.hefty-gardenia-butterfly-744db6889-4bk7w.1420.0 | Other | 5.6 KB | 3e6d699b25d5 | | runs/Jan31_22-09-18_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738361361.hefty-gardenia-butterfly-744db6889-4bk7w.1713.0 | Other | 6.0 KB | ea2277a477bd | | runs/Jan31_22-14-35_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738361678.hefty-gardenia-butterfly-744db6889-4bk7w.2090.0 | Other | 9.7 KB | 2ca465173c1f | | .gitattributes | Repository | 1.6 KB | — | | merges.txt | Tokenizer | 1.7 MB | — | | tokenizer.json | Tokenizer | 11.4 MB | 9c5ae00e602b | | tokenizer_config.json | Tokenizer | 7.3 KB | — | | vocab.json | Tokenizer | 2.8 MB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 988.1 MB [Download from Convergent Intelligence](https://huggingface.co/reaperdoesntknow/DeepReasoning_1R) Released by Convergent Intelligence through its official repository on Hugging Face. ## Built From - Derived from [Qwen/Qwen2.5-0.5B-Instruct](https://savrn.com/models/qwen2-5-0-5b-instruct) - Trained on (disclosed) HumanLLMs/Human-Like-DPO-Dataset ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 988.1 MB | | 16-bit | 1.0 GB | | 8-bit | 0.5 GB | | 4-bit | 0.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About DeepReasoning_1R ### How much GPU memory does DeepReasoning_1R need? About 1.2 GB at 16-bit and 0.3 GB at 4-bit: the weights (494M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run DeepReasoning_1R 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. ### What is DeepReasoning_1R's context length? 32,768 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Qwen2.5-0.5B-Instruct](https://savrn.com/models/qwen2-5-0-5b-instruct) [Qwen](https://savrn.com/model-publishers/qwen) Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and… Open weights apache-2.0 494M parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-0-5b-instruct) Model · Text generation ### [Qwen2.5-0.5B](https://savrn.com/models/qwen2-5-0-5b) [Qwen](https://savrn.com/model-publishers/qwen) Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and… Open weights apache-2.0 494M parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-0-5b) Model · Text generation ### [Qwen2-0.5B](https://savrn.com/models/qwen2-0-5b) [Qwen](https://savrn.com/model-publishers/qwen) Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the 0.5B Qwen2 base language model. Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc. For more details, please refer to our blog… Open weights apache-2.0 494M parameters 131,072 tokens transformers [View model](https://savrn.com/models/qwen2-0-5b) Model · Text generation ### [qwen2.5-0.5b-topo-governed-cbp-fineweb](https://savrn.com/models/qwen2-5-0-5b-topo-governed-cbp-fineweb) [Frank Morales](https://savrn.com/model-publishers/frankmorales2020) article: https://medium.com/ai-simplified-in-plain-english/the-architecture-of-permanence-how-topo-cbp-tamed-the-uncharted-stream-a17c1d8425af article-2: https://medium.com/@frankmorales91352/the-silicon-hippocampus-reverse-engineering-300-million-years-of-memory-and-the-final-conquest-of-579bef471e03 article-3: https://medium.com/ai-simplified-in-plain-english/the-architecture-of-permanence-how-topological-continual-backpropagation-redefines-machine-cf51ad83de12 article-4: https://medium.com/ai-simplified-in-plain-english/the-architecture-of-permanence-completing-continual-backpropagation-reversing-300-million-years-ed16739b824e full code-2… Open weights apache-2.0 494M parameters 32,768 tokens [View model](https://savrn.com/models/qwen2-5-0-5b-topo-governed-cbp-fineweb) Model · Text generation ### [math-slm-qwen2.5-0.5b-v4](https://savrn.com/models/math-slm-qwen2-5-0-5b-v4) [Mandavi Singh](https://savrn.com/model-publishers/singhmandavi) A domain-specific small language model for step-by-step math problem solving, built by team03 (SLM Learners) for the Pramana SLM++ Bootcamp Round 2 submission. For an OpenAI-compatible endpoint, serve with servehf.py (stdlib + transformers only, no Ollama needed). Precision note: training ran in bf16 compute (QLoRA 4-bit NF4 base), but the merged checkpoint uploaded here is float16 (the merge step reloads the base in fp16). - Public Hugging Face datasets pulled via pulldata.py; licenses verified through the HF API on 2026-09-05 and recorded in datamanifest.md. - Held-out eval set built with buildheldouteval.py from raw ExamBench rows never used in training, with a final overlap check that… Open weights apache-2.0 494M parameters 32,768 tokens [View model](https://savrn.com/models/math-slm-qwen2-5-0-5b-v4) Model · Text generation ### [Lurfa-1.3](https://savrn.com/models/lurfa-1-3) [Noeme](https://savrn.com/model-publishers/noeme) 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). Open weights 494M parameters 32,768 tokens transformers [View model](https://savrn.com/models/lurfa-1-3) ## Convergent Intelligence [All models and datasets](https://savrn.com/model-publishers/reaperdoesntknow) ## Versions - [9860b339489d](https://savrn.com/models/deepreasoning-1r/versions/9860b339489d) · current 2026-09-18 ## 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 2026-10-21. - [Hugging Face record](https://huggingface.co/reaperdoesntknow/DeepReasoning_1R) - [How the hub is built](https://savrn.com/model-hub/methodology)