Spyfood Brain V2 is an open-source language model by Spyfood. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.3.
4bit Conversational Endpoints compatible Gguf Instruct Llama.cpp Quantized Qwen2 Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/Spyfood/Spyfood-brain-v2
Spyfood Brain V2 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)
Spyfood Brain V2 Parameters and Internals
| LLM Name | Spyfood Brain V2 |
| Repository 🤗 | https://huggingface.co/Spyfood/Spyfood-brain-v2 |
| Model Name | unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2026-07-07 |
| Maintainer | Spyfood |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf|4bit |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Spyfood Brain V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| VibeThinker 3B Heretic | 128K / 6.2 GB | 1016 | 4 |
| TINY THINKER INSTRUCT | 32K / 6.2 GB | 756 | 3 |
| Zenith 3B | 32K / 6.3 GB | 190 | 3 |
| Coder GRPO 3B | 32K / 6.2 GB | 1209 | 7 |
| OpenCogito | 32K / 6.2 GB | 779 | 0 |
| OpenCognito R1 | 32K / 6.1 GB | 655 | 0 |
| Qwen2.5 3B Instruct Heretic | 32K / 6.2 GB | 100 | 1 |
| Nomi 1 Creative | 32K / 6.2 GB | 47 | 2 |
| Tiny Agent A 3B | 32K / 6.2 GB | 785 | 24 |
| Esbieta Ec Qwen 2.5 3B | 32K / 6.2 GB | 16 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Spyfood/Spyfood-brain-v2 .
Rank the Spyfood Brain V2 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? 54868 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