Autotrain compatible Base model:quantized:state-spa... Base model:state-spaces/mamba-... Gguf Mamba Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/leliuga/mamba-2.8b-hf-GGUF
Mamba 2.8B Hf GGUF 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)
Mamba 2.8B Hf GGUF Parameters and Internals
| Model Type |
|
| LLM Name | Mamba 2.8B Hf GGUF |
| Repository 🤗 | https://huggingface.co/leliuga/mamba-2.8b-hf-GGUF |
| Model Name | mamba-2.8b-hf |
| Model Creator | State Space Models |
| Base Model(s) | |
| Model Size | 2.8b |
| Required VRAM | 1.4 GB |
| Updated | 2025-10-04 |
| Maintainer | leliuga |
| Model Type | mamba |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | MambaForCausalLM |
| License | apache-2.0 |
| Vocabulary Size | 50280 |
| Torch Data Type | float32 |
Best Alternatives to Mamba 2.8B Hf GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mamba 2.8B Hf | 0K / 11.1 GB | 15982 | 111 |
| Clinicalmamba 2.8B Hf | 0K / 11.1 GB | 25 | 3 |
| Mamba 2.8B Zephyr Hf | 0K / 11.1 GB | 12 | 0 |
| Mamba 2.8B Ultrachat Hf | 0K / 11.1 GB | 4 | 1 |
| Mamba 2.8B Slimpj Hf | 0K / 11.1 GB | 6 | 0 |
| Mamba 2.8B | 0K / 5.6 GB | 8 | 1 |
| Mamba 2.8B Slimpj | 0K / 5.6 GB | 7 | 0 |
| Mamba Ko 2.8B | 0K / 5.8 GB | 15 | 18 |
Note: green Score (e.g. "73.2") means that the model is better than leliuga/mamba-2.8b-hf-GGUF .
Rank the Mamba 2.8B Hf GGUF 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? 51566 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124