ChimeraLlama 3 8B V2 is an open-source language model by mlabonne. Features: 8b LLM, VRAM: 16GB, Context: 8K, License: other, Instruction-Based, Merged, HF Score: 69.7, LLM Explorer Score: 0.24, Arc: 63.8, HellaSwag: 80.9, MMLU: 67.8, TruthfulQA: 56.5, WinoGrande: 76, GSM8K: 73.
Merged Model Base model:cloudyu/meta-llama-... Base model:dphn/dolphin-2.9-ll... Base model:locutusque/llama-3-... Base model:mlabonne/orpollama-... Base model:nousresearch/meta-l... Base model:vicgalle/configurab... Endpoints compatible Instruct Llama Model-index Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v2
ChimeraLlama 3 8B V2 Benchmarks
MMLU Pro: 28.54
GPQA: 4.7
MUSR: 5.25
BBH: 28.48
IFEval: 44.69 vs 88 (so35)-49.2%
ARC: 63.82 vs 96.7 (so35)-34%
HellaSwag: 80.94 vs 95.3 (gpt4)-15.1%
MMLU: 67.83 vs 88.3 (so35)-23.2%
TruthfulQA: 56.53 vs 59 (gpt4)-4.2%
WinoGrande: 76.01 vs 87.5 (gpt4)-13.1%
GSM8K: 73.01 vs 96.4 (so35)-24.3%
MATH Lvl 5: 9.06
LLME Score: 0.23529
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)
ChimeraLlama 3 8B V2 Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | ChimeraLlama 3 8B V2 |
| Repository 🤗 | https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v2 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 8b |
| Required VRAM | 16 GB |
| Updated | 2026-01-05 |
| Maintainer | mlabonne |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to ChimeraLlama 3 8B V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...otron 8B UltraLong 4M Instruct | 4192K / 32.1 GB | 89 | 119 |
| ...a 3.1 8B UltraLong 4M Instruct | 4192K / 32.1 GB | 176 | 24 |
| UltraLong Thinking | 4192K / 16.1 GB | 9 | 3 |
| ...a 3.1 8B UltraLong 2M Instruct | 2096K / 32.1 GB | 875 | 9 |
| ...otron 8B UltraLong 2M Instruct | 2096K / 32.1 GB | 40 | 17 |
| Cthulhu 8B V1.4 | 1048K / 16.1 GB | 13 | 9 |
| ...otron 8B UltraLong 1M Instruct | 1048K / 32.1 GB | 3440 | 55 |
| ...a 3.1 8B UltraLong 1M Instruct | 1048K / 32.1 GB | 1387 | 29 |
| Zero Llama 3.1 8B Beta6 | 1048K / 16.1 GB | 5 | 1 |
| ...dger Nu Llama 3.1 8B UltraLong | 1048K / 16.2 GB | 5 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/ChimeraLlama-3-8B-v2 .
Rank the ChimeraLlama 3 8B 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? 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