Model Card on HF 🤗: https://huggingface.co/liminerity/MISTRAL-1.58-BIT-PRETRAIN-v2
MISTRAL 1.58 BIT PRETRAIN V2 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MISTRAL 1.58 BIT PRETRAIN V2 Parameters and Internals
| LLM Name | MISTRAL 1.58 BIT PRETRAIN V2 |
| Repository 🤗 | https://huggingface.co/liminerity/MISTRAL-1.58-BIT-PRETRAIN-v2 |
| Model Size | 1.1b |
| Required VRAM | 4.3 GB |
| Updated | 2025-06-09 |
| Maintainer | liminerity |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to MISTRAL 1.58 BIT PRETRAIN V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Hare 1.1B Base 0.5v | 32K / 2.4 GB | 47 | 0 |
| TinyLlama Mistral | 32K / 4.4 GB | 11 | 2 |
| Mistral 1.1B Testing | 32K / 4.4 GB | 3610 | 1 |
| Hare 1.1B Base | 32K / 2.2 GB | 81 | 7 |
| Hare 1.1B Chat | 32K / 2.2 GB | 37 | 0 |
| Dipsmol | 32K / 2.2 GB | 9 | 0 |
| Hare 1.1B Tool | 32K / 2.2 GB | 10 | 1 |
| Stealth Rag V1.1 | 32K / 14.4 GB | 18 | 0 |
| Stealth Rag V1 E1 | 32K / 14.4 GB | 18 | 1 |
| Mallam 1.1B 4096 | 32K / 2.2 GB | 459 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than liminerity/MISTRAL-1.58-BIT-PRETRAIN-v2 .
Rank the MISTRAL 1.58 BIT PRETRAIN V2 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124