Mistral AI · 12B · Dense
Multilingual 12B with 128K context
436.8K downloads
1.7K likes
2024-07 128K context
Use Cases
chat multilingual
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 4.3 GB | low | — |
| Q3_K_M | 3 | 5.9 GB | moderate | — |
| Q4_K_M | 4 | 6.6 GB | good | — |
| Q5_K_M | 5 | 8.2 GB | good | — |
| Q6_K | 6 | 9.7 GB | excellent | — |
| Q8_0 | 8 | 12.8 GB | excellent | — |
| F16 | 16 | 25.1 GB | lossless | — |
GPUs that run Mistral Nemo 12B
Mistral Nemo 12B needs about 6.6 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 8 GB of VRAM or more (140 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 8 GB | RTX 5060 Ti , RX 7600 , Arc A750 |
| 10 GB | RTX 3080 , RX 6700M |
| 11 GB | RTX 2080 Ti , GTX 1080 Ti |
| 12 GB | RTX 5070 , RX 7700 XT , RTX 4070 Ti |
About this model
Mistral NeMo is a 12B model built in collaboration with NVIDIA. Mistral NeMo offers a large context window of up to 128k tokens. Its reasoning, world knowledge, and coding accuracy are state-of-the-art in its size category. As it relies on standard architecture, Mistral NeMo is easy to use and a drop-in replacement in any system using Mistral 7B.