SmolLM2 360M Merged is an open-source language model by vonjack. Features: 360m LLM, VRAM: 0.7GB, Context: 8K, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.18.
Merged Model Arxiv:2306.01708 Base model:huggingfacetb/smoll... Base model:huggingfacetb/smoll... Conversational Endpoints compatible Gguf Instruct Llama Model-index Q8 Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/vonjack/SmolLM2-360M-Merged
SmolLM2 360M Merged Benchmarks
MMLU Pro: 1.09
GPQA: 0.78
MUSR: 3.36
BBH: 4.74
IFEval: 32.06 vs 88 (so35)-63.6%
MATH Lvl 5: 1.74
LLME Score: 0.18439
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)
SmolLM2 360M Merged Parameters and Internals
| LLM Name | SmolLM2 360M Merged |
| Repository 🤗 | https://huggingface.co/vonjack/SmolLM2-360M-Merged |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 360m |
| Required VRAM | 0.7 GB |
| Updated | 2026-03-23 |
| Maintainer | vonjack |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q8|gguf |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to SmolLM2 360M Merged
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 360M Bnb 4bit | 8K / 0.3 GB | 1870 | 2 |
| SmolLM2 360M Instruct Bnb 4bit | 8K / 0.3 GB | 475 | 1 |
| SmolLM 360M Instruct 8bit | 2K / 0.4 GB | 19 | 2 |
| SmolLM2 360M Instruct | 8K / 0.7 GB | 446881 | 185 |
| Smollm3 720prms | 8K / 0.7 GB | 46 | 0 |
| ProseFlow V1 360M Instruct | 8K / 0.7 GB | 8 | 0 |
| SmolLM2 Rethink 360M | 8K / 1.4 GB | 7 | 1 |
| SolaraV2 Coder 0511 | 8K / 0.7 GB | 5 | 1 |
| BrainrotLM Assistant 362M | 8K / 0 GB | 7 | 0 |
| SmolLM2 CoT 360M | 8K / 1.4 GB | 81 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than vonjack/SmolLM2-360M-Merged .
Rank the SmolLM2 360M Merged 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