12.25B Mistral record
Captured configuration records MistralForCausalLM and Safetensors metadata reports 12,247,782,400 parameters.
Open Source Model Profile · riple-saanvi-lab
Saanvi-C0-12B
Saanvi-C0-12B is a 12.25B-parameter Mistral-family text-generation model from riple-saanvi-lab with Apache-2.0 licensing.
- Publisher
- riple-saanvi-lab
- Task
- text-generation
- Model type
- mistral
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Saanvi-C0-12B is published by riple-saanvi-lab as a Mistral-family text-generation model. The captured configuration identifies MistralForCausalLM and Safetensors metadata reports 12,247,782,400 parameters. According to the model card, the publisher presents it as a 12B model tuned for speed, efficiency, and contextual accuracy.
Recorded capabilities
Apache-2.0 record
Card data records apache-2.0, and the model card restates Apache 2.0 licensing.
Publisher-claimed efficiency stack
According to the model card, the publisher claims 4-bit quantization, Flash Attention 2 with up to 2.7x speedup language, and reduced VRAM usage.
Documented Transformers usage
According to the model card, a bfloat16 Transformers snippet with install instructions and publisher throughput and VRAM figures is provided.
Use cases in the source record
- Conversational text-generation workflows using the model card's documented bfloat16 Transformers snippet.
- Efficiency-oriented experiments that reference the publisher's claimed 4-bit quantization and VRAM figures, treated as unverified publisher claims.
Limitations and unknowns
- No independently verified evaluation results were extracted from this record; throughput and latency figures in the card are publisher claims.
- The 128k context window appears only as a model-card publisher claim and was not independently verified.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: riple-saanvi-lab/Saanvi-C0-12B
Captured: Unknown. Processed: 2026-09-07T19:35:29.633013+00:00.
Saanvi-C0-12B 🤖⚡ A next-generation 12B LLM optimized for speed, efficiency, and contextual accuracy. Powered by RAG-based enhancements • 4-bit quantization • Flash Attention 2 • bfloat16 • 128k context window 🚀 Why Upgrade to Saanvi-C0-12B? Saanvi-C0-12B brings a huge leap in capability over smaller models, maintaining efficiency while significantly improving reasoning, fluency, and task completion and math! Feature Benefit ⚡ Flash Attention 2 Up to 2.7× faster inference 🧠 4-bit Quantization Runs on 8GB VRAM GPUs 🎯 Instruction-Tuned Better task performance 🔥 RAG-Enhanced More precise contextual retrieval ➗ Math-Expert Precise M…
F001F002F003F004F005F006F007F008F010F011F012F014F015F016F017