Tinymistral 950M is an open-source language model by cckm. Features: 950m LLM, VRAM: 1.9GB, Context: 32K, License: mit, LLM Explorer Score: 0.19.
Base model:cckm/tinymistral 95... Base model:finetune:cckm/tinym... Dataset:huggingfacefw/fineweb Dataset:tiiuae/falcon-refinedw... En Mistral Pytorch Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/cckm/tinymistral_950m
Tinymistral 950m Benchmarks
MMLU Pro: 1.07
GPQA: 1.34
MUSR: 2.05
BBH: 2.37
IFEval: 23.95 vs 88 (so35)-72.8%
MATH Lvl 5: 0.53
LLME Score: 0.18813
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 950M Parameters and Internals
| LLM Name | Tinymistral 950m |
| Repository 🤗 | https://huggingface.co/cckm/tinymistral_950m |
| Base Model(s) | |
| Model Size | 950m |
| Required VRAM | 1.9 GB |
| Updated | 2026-03-30 |
| Maintainer | cckm |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 32009 |
| Torch Data Type | bfloat16 |
Rank the Tinymistral 950M 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? 52721 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