Falcon 40B Gptq is an open-source language model by wyklq. Features: 40b LLM, VRAM: 23.3GB, Quantized, LLM Explorer Score: 0.08.
| Additional Notes |
|
| LLM Name | Falcon 40B Gptq |
| Repository ๐ค | https://huggingface.co/wyklq/falcon-40b-gptq |
| Model Size | 40b |
| Required VRAM | 23.3 GB |
| Updated | 2026-04-02 |
| Maintainer | wyklq |
| Model Type | RefinedWeb |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | RWForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.30.2 |
| Is Biased | 0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 65024 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Alfred 40B 1023 GPTQ | 0K / 22.5 GB | 9 | 3 |
| FalconLite | 0K / 22.3 GB | 349 | 170 |
| FalconLite | 0K / 22.3 GB | 315 | 170 |
| Falcon 40B Instruct GPTQ | 0K / 22.5 GB | 321 | 197 |
| ...st1 En 2048 Falcon 40B V2 GPTQ | 0K / 22.5 GB | 10 | 8 |
| Falcon 40B Gptq | 0K / 23.4 GB | 25 | 15 |
| Falcon 40B Instruct GPTQ | 0K / 22.5 GB | 4 | 1 |
| ...truct GPTQ Inference Endpoints | 0K / 22.5 GB | 5 | 2 |
| Falcon 40B 8bit | 0K / 41.8 GB | 4 | 1 |
| ...dLM Uncensored Falcon 40B GPTQ | 0K / 22.5 GB | 15 | 60 |
๐ 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! ๐