# Open-Weight Models Under osl-3.0: Open-Weight AI Source: https://savrn.com/models/licenses/osl-3-0 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by License # Open-Weight Models Under osl-3.0 6 open-weight models released under osl-3.0 in the SAVRN Model Hub, with Convergent Intelligence and Sandia Beltran publishing the most. 6Models 2Publishers 1B to 1BParameter range 1Licenses ## SAVRN's Take Five models on our hub carry osl-3.0, and all five come from one publisher, Convergent Intelligence. We have not summarized what this license permits for commercial use; the license text governs. For an operator that puts one task ahead of every other: before the weights go into a rack that serves paying customers, someone on your side reads the full license and decides whether serving, modifying and redistributing the model fits the terms as written. Do that review before the purchase order, not after. All five are text generation models on the Gemma3ForCausalLM architecture, and each is a weight-level merge of Gemma-3 (1B) and Qwen-3 (0.6B), tuned afterward for stepwise reasoning. The three we size, Qemma-Q14B, Qemma-Q1.7B and Qemma-GEI, hold about 1 billion parameters and need 2.4 GB at 16-bit, 1.2 GB at 8-bit and 0.6 GB at 4-bit, with the cheapest host we track at a single MI300X for $1.85 an hour. At that footprint, memory is not what drives the hardware choice. Context length is where they separate: Qemma-Q14B takes 524,288 tokens, Qemma-Q1.7B 262,144, Qemma-GEI 131,072, and Qemma-sft and Qemma-redux 32,768 each. Downloads sit in a narrow band. Qemma-sft leads at 3,832 a month, Qemma-redux follows at 3,808, then Qemma-Q14B at 3,738, Qemma-Q1.7B at 3,691 and Qemma-GEI at 3,634. Read the license text first, then choose by context length; memory and host price are the same across the three we size. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [Qemma-sft](https://savrn.com/models/qemma-sft) | Convergent Intelligence | — | osl-3.0 | 3.8k | — | | [Qemma-redux](https://savrn.com/models/qemma-redux) | Convergent Intelligence | — | osl-3.0 | 3.8k | — | | [Qemma-Q14B](https://savrn.com/models/qemma-q14b) | Convergent Intelligence | 1B | osl-3.0 | 3.7k | 1x MI300X, $1.85/hr | | [Qemma-Q1.7B](https://savrn.com/models/qemma-q1-7b) | Convergent Intelligence | 1B | osl-3.0 | 3.7k | 1x MI300X, $1.85/hr | | [Qemma-GEI](https://savrn.com/models/qemma-gei) | Convergent Intelligence | 1B | osl-3.0 | 3.6k | 1x MI300X, $1.85/hr | | [Opensaint](https://savrn.com/models/opensaint) | Sandia Beltran | — | osl-3.0 | — | — | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) | 5 | | [Sandia Beltran](https://savrn.com/model-publishers/sandia12) | 1 | ## All 6 Models Model · Text generation ### [Qemma-Q14B](https://savrn.com/models/qemma-q14b) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions. This Model underwent an additional merge between Qemma-redux and Qwen3-14B, in addition to adding Rope Scaling. Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (14B) at the weight level (no adapters). This variant uses Yarn based Rope Scaling with 1: Ratio from maxpositionembeddings = 524288 Gemma-3 backbone (26 layers, hidden 1152, MLP 6912) Qwen-style attention regrouped to Gemma’s 4×256 heads. (headdim=128, hidden=5120… Open weights osl-3.0 1B parameters 524,288 tokens transformers [View model](https://savrn.com/models/qemma-q14b) Model · Text generation ### [Qemma-Q1.7B](https://savrn.com/models/qemma-q1-7b) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions. This Model underwent an additional merge between Qemma-redux and Qwen3-1.7B, in addition to adding Rope Scaling. Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (1.7B) at the weight level (no adapters). This variant uses Yarn based Rope Scaling with 1: Ratio from maxpositionembeddings = 242144 Gemma-3 backbone (26 layers, hidden 1152, MLP 6912) Qwen-style attention regrouped to Gemma’s 4×256 heads. (headdim=128, hidden=2048… Open weights osl-3.0 1B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qemma-q1-7b) Model · Text generation ### [Qemma-GEI](https://savrn.com/models/qemma-gei) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions. This Model underwent an additional merge between Qemma-redux and Qwen3-0.6B, in addition to adding Rope Scaling. Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (0.6B) at the weight level (no adapters). This variant uses Yarn based Rope Scaling with 1:1 Ratio from maxpositionembeddings Use: research, instruction following, code/help, analysis, further SFT/RLHF. Limits: may hallucinate; not for safety-critical, medical, legal… Open weights osl-3.0 1B parameters 131,072 tokens transformers [View model](https://savrn.com/models/qemma-gei) Model · Text generation ### [Qemma-sft](https://savrn.com/models/qemma-sft) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (0.6B) at the weight level (no adapters). Design: Gemma MLP/body + Qwen attention/head, projected and aligned to Gemma’s hidden size. The model is then SFT-tuned for stepwise reasoning. Use: research, instruction following, code/help, analysis, further SFT/RLHF. Limits: may hallucinate; not for safety-critical, medical, legal, or financial decisions. Follow dataset/model licenses. ~512 warm-start steps (Alpaca-style data) 256 Additional pretraining steps on (O1-OPEN/OpenO1-SFT) 128 SFT steps with (Jackrong/gpt-oss-120b-reasoning-STEM-5K) 256 SFT steps with (O1-OPEN/OpenO1-SFT) This model is part of the Convergent… Open weights osl-3.0 32,768 tokens transformers [View model](https://savrn.com/models/qemma-sft) Model · Text generation ### [Qemma-redux](https://savrn.com/models/qemma-redux) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) Redux This Model underwent an additional merge between Qemma-sft and Qwen3-0.6B, in addition to adding Rope Scaling. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (0.6B) at the weight level (no adapters). Design: Gemma MLP/body + Qwen attention/head, projected and aligned to Gemma’s hidden size. The model is then SFT-tuned for stepwise reasoning. This variant uses Yarn based Rope Scaling with 1:1 Ratio from maxpositionembeddings Use: research, instruction following, code/help, analysis, further SFT/RLHF. Limits: may hallucinate; not for safety-critical, medical, legal, or financial decisions. Follow dataset/model licenses. ~512 warm-start steps (Alpaca-style… Open weights osl-3.0 32,768 tokens transformers [View model](https://savrn.com/models/qemma-redux) Model ### [Opensaint](https://savrn.com/models/opensaint) [Sandia Beltran](https://savrn.com/model-publishers/sandia12) Open weights osl-3.0 [View model](https://savrn.com/models/opensaint) ## Questions ### Which osl-3.0 models are most downloaded? By monthly downloads reported by the Hugging Face Hub: Qemma-Q14B (3.7k); Qemma-Q1.7B (3.7k); Qemma-GEI (3.6k). ## Other Licenses - [apache-2.0](https://savrn.com/models/licenses/apache-2-0) 3285 - [mit](https://savrn.com/models/licenses/mit) 1305 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 209 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 164 - [bsd-3-clause](https://savrn.com/models/licenses/bsd-3-clause) 108 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) 52 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 40 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32 - [unknown](https://savrn.com/models/licenses/unknown) 32 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 28 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 [See all](https://savrn.com/models/licenses)