Autotrain compatible Base model:finetune:tiiuae/fal... Base model:tiiuae/falcon3-10b-... Conversational Dataset:fluently-sets/ultrathi... Demo En Endpoints compatible Falcon Falcon3 Fluently-lm Fluently-sets Instruct Llama Reasoning Region:us Safetensors Sft Sharded Tensorflow Thinking Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/fluently-sets/FalconThink3-10B-IT
FalconThink3 10B IT Benchmarks
MMLU Pro: 38.16
GPQA: 11.3
MUSR: 15.55
BBH: 44.98
IFEval: 73.26 vs 88 (so35)-16.8%
MATH Lvl 5: 24.47
LLME Score: 0.34818
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)
FalconThink3 10B IT Parameters and Internals
| LLM Name | FalconThink3 10B IT |
| Repository 🤗 | https://huggingface.co/fluently-sets/FalconThink3-10B-IT |
| Base Model(s) | |
| Model Size | 10b |
| Required VRAM | 20.5 GB |
| Updated | 2025-02-22 |
| Maintainer | fluently-sets |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 131072 |
| Torch Data Type | float16 |
Best Alternatives to FalconThink3 10B IT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Falcon3 10B Instruct | 32K / 20.5 GB | 32170 | 93 |
| Falcon3 10B Tensopolis V1 | 32K / 20.5 GB | 159 | 0 |
| BuddyGlassUncensored2025.2 | 32K / 20.5 GB | 164 | 3 |
| ...essi V0.2 Falcon3 10B Instruct | 32K / 20.5 GB | 8 | 0 |
| ...essi V0.1 Falcon3 10B Instruct | 32K / 20.5 GB | 12 | 0 |
| Barcenas 10B | 32K / 20.5 GB | 12 | 1 |
| Eyas 17B Instruct | 32K / 34.8 GB | 6 | 0 |
| Falcon3Slerp2 10B | 32K / 20.5 GB | 11 | 0 |
| RA Reasoner | 32K / 20.5 GB | 36 | 2 |
| FalconSlerp3 10B | 32K / 20.5 GB | 10 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than fluently-sets/FalconThink3-10B-IT .
Rank the FalconThink3 10B IT 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227