Pico Lamma 3.2 1B Reasoning Instruct is an open-source language model by Predacon. Features: 1b LLM, VRAM: 1.1GB, Context: 128K, License: agpl-3.0, Instruction-Based, LLM Explorer Score: 0.15.
4-bit Base model:meta-llama/llama-3.... Base model:quantized:meta-llam... Bitsandbytes En Instruct Llama Predacons Problem solving Reasoning Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Predacon/Pico-Lamma-3.2-1B-Reasoning-Instruct
Pico Lamma 3.2 1B Reasoning Instruct 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)
Pico Lamma 3.2 1B Reasoning Instruct Parameters and Internals
| LLM Name | Pico Lamma 3.2 1B Reasoning Instruct |
| Repository 🤗 | https://huggingface.co/Predacon/Pico-Lamma-3.2-1B-Reasoning-Instruct |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 1.1 GB |
| Updated | 2026-06-04 |
| Maintainer | Predacon |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | agpl-3.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Pico Lamma 3.2 1B Reasoning Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 8363204 | 1460 |
| LlaMa3.2 1B Instruct | 128K / 4.9 GB | 142 | 0 |
| Llama 3.2 1B Instruct Bf16 | 128K / 2.5 GB | 1158 | 5 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 422778 | 96 |
| ...2 1B Instruct Only Mask W Item | 128K / 3 GB | 1225 | 0 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 7 | 0 |
| ...Instruct Only Mask W Item Mesh | 128K / 3 GB | 390 | 0 |
| Shield Llama 3.2 1B Full FT CE | 128K / 2.5 GB | 795 | 0 |
| Llama3.2 1B RolePlaying Full | 128K / 2.5 GB | 45 | 1 |
| Llama3.2 1B FantasySciFi | 128K / 2.5 GB | 304 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Predacon/Pico-Lamma-3.2-1B-Reasoning-Instruct .
Rank the Pico Lamma 3.2 1B Reasoning Instruct 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? 54413 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