Autotrain compatible Conversational En Endpoints compatible Mergekit Qwen2 Region:us Safetensors Sharded Tensorflow Zh
Model Card on HF 🤗: https://huggingface.co/leafspark/Iridium-72B-v0.1
Iridium 72B V0.1 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)
Iridium 72B V0.1 Parameters and Internals
| LLM Name | Iridium 72B V0.1 |
| Repository 🤗 | https://huggingface.co/leafspark/Iridium-72B-v0.1 |
| Model Size | 72b |
| Required VRAM | 2.5 GB |
| Updated | 2025-09-23 |
| Maintainer | leafspark |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en zh |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.1 |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Iridium 72B V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...R10528DistillQwen 72B Preview3 | 195K / 146 GB | 15 | 6 |
| Kimi Dev 72B | 128K / 83.4 GB | 6066 | 367 |
| Qwen2.5 72B | 128K / 145.5 GB | 30424 | 78 |
| Ultiima 72B | 128K / 146.1 GB | 74 | 3 |
| Homer V1.0 Qwen2.5 72B | 128K / 146.1 GB | 126 | 6 |
| Ultiima 72B V1.5 | 128K / 146.1 GB | 24 | 0 |
| AceInstruct 72B | 128K / 146 GB | 212 | 17 |
| EVA Qwen2.5 72B V0.2 | 128K / 146 GB | 187 | 22 |
| Qwen2 72B | 128K / 145.5 GB | 11962 | 199 |
| ...n2.5 72B 2x Instruct TIES V1.0 | 128K / 146.1 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than leafspark/Iridium-72B-v0.1 .
Rank the Iridium 72B V0.1 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? 51535 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124