Laserxtral is an open-source language model by cognitivecomputations. Features: 7b LLM, VRAM: 48.3GB, Context: 32K, License: cc-by-nc-2.0, HF Score: 72.3, LLM Explorer Score: 0.14, Arc: 69, HellaSwag: 86.8, MMLU: 64.7, TruthfulQA: 63.8, WinoGrande: 80, GSM8K: 69.8.
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/laserxtral
Laserxtral Benchmarks
ARC: 69.03 vs 96.7 (so35)-28.6%
HellaSwag: 86.76 vs 95.3 (gpt4)-9%
MMLU: 64.68 vs 88.3 (so35)-26.7%
TruthfulQA: 63.8 vs 59 (gpt4)8.1%
WinoGrande: 80.03 vs 87.5 (gpt4)-8.5%
GSM8K: 69.75 vs 96.4 (so35)-27.6%
LLME Score: 0.13874
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)
Laserxtral Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Laserxtral |
| Repository 🤗 | https://huggingface.co/cognitivecomputations/laserxtral |
| Model Size | 7b |
| Required VRAM | 48.3 GB |
| Updated | 2025-07-13 |
| Maintainer | cognitivecomputations |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | cc-by-nc-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Laserxtral
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Multimaster 7B V6 | 32K / 142.5 GB | 8428 | 1 |
| MultiverseBuddy 15B MoE | 32K / 25.8 GB | 9 | 0 |
| Mini Mixtral V0.2 | 32K / 25.8 GB | 6 | 4 |
| Multilingual Mistral | 32K / 93.5 GB | 724 | 2 |
| OpenMistral MoE | 32K / 48.3 GB | 1218 | 0 |
| Lumina 2 | 32K / 37.1 GB | 9 | 0 |
| Rawr | 32K / 93.5 GB | 1302 | 0 |
| Merged Model MoE | 32K / 53.3 GB | 4 | 1 |
| RogerWizard 12B MoE | 32K / 25.8 GB | 4 | 1 |
| StarlingMaths 12B MoE | 32K / 25.8 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/laserxtral .
Rank the Laserxtral 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? 52628 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