TinyMistral 6x248M is an open-source language model by M4-ai. Features: 1b LLM, VRAM: 4GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.12.
Base model:felladrin/tinymistr... Base model:jtatman/tinymistral... Base model:locutusque/tinymist... Base model:locutusque/tinymist... Base model:locutusque/tinymist... Base model:locutusque/tinymist... Base model:merge:felladrin/tin... Base model:merge:jtatman/tinym... Base model:merge:locutusque/ti... Base model:merge:locutusque/ti... Base model:merge:locutusque/ti... Base model:merge:locutusque/ti... Dataset:nampdn-ai/mini-pes2o Endpoints compatible Felladrin/tinymistral-248m-sft... Frankenmoe Instruct Jtatman/tinymistral-v2-pycoder... Lazymergekit Locutusque/tinymistral-248m-v2 Locutusque/tinymistral-248m-v2... Locutusque/tinymistral-248m-v2... Locutusque/tinymistral-248m-v2... Merge Mergekit Mixtral Moe Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/M4-ai/TinyMistral-6x248M
TinyMistral 6x248M 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)
TinyMistral 6x248M Parameters and Internals
| Model Type |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | TinyMistral 6x248M |
| Repository 🤗 | https://huggingface.co/M4-ai/TinyMistral-6x248M |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 4 GB |
| Updated | 2026-03-29 |
| Maintainer | M4-ai |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|bos|> |
| Vocabulary Size | 32005 |
| Torch Data Type | float32 |
Best Alternatives to TinyMistral 6x248M
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TinyMistral 6x248M Instruct | 32K / 4 GB | 12 | 11 |
Note: green Score (e.g. "73.2") means that the model is better than M4-ai/TinyMistral-6x248M .
Rank the TinyMistral 6x248M 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? 52392 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a