8-bit Autotrain compatible Base model:quantized:tiiuae/fa... Base model:tiiuae/falcon-h1-34... Conversational Endpoints compatible Falcon-h1 Falcon h1 Gptq Instruct Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int8
Falcon H1 34B Instruct GPTQ Int8 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)
Falcon H1 34B Instruct GPTQ Int8 Parameters and Internals
| LLM Name | Falcon H1 34B Instruct GPTQ Int8 |
| Repository 🤗 | https://huggingface.co/tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int8 |
| Base Model(s) | |
| Model Size | 34b |
| Required VRAM | 44.3 GB |
| Updated | 2025-06-01 |
| Maintainer | tiiuae |
| Model Type | falcon_h1 |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | FalconH1ForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.52.0.dev0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 261120 |
| Torch Data Type | bfloat16 |
Best Alternatives to Falcon H1 34B Instruct GPTQ Int8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Falcon H1 34B Instruct | 256K / 67 GB | 2635 | 29 |
Note: green Score (e.g. "73.2") means that the model is better than tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int8 .
Rank the Falcon H1 34B Instruct GPTQ Int8 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227