Pixtral-Large-Instruct-2411 🧡 ExLlamaV2 4.5bpw Quant
4.5bpw quant of Pixtral-Large-Instruct.
Vision inputs working on dev branch of ExLlamaV2.
Tokenizer And Prompt Template
Using conversion of v7m1 tokenizer with 32k vocab size.
Chat template in chat_template.json uses the v7 instruct template:
<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST]
Available Sizes
| Repo | Bits | Head Bits | Size |
|---|---|---|---|
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-2.0bpw | 2.0 | 6.0 | 35.18 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-2.5bpw | 2.5 | 6.0 | 39.34 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-3.0bpw | 3.0 | 6.0 | 46.42 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-3.5bpw | 3.5 | 6.0 | 53.50 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-4.0bpw | 4.0 | 6.0 | 60.61 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-4.5bpw | 4.5 | 6.0 | 67.68 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-5.0bpw | 5.0 | 6.0 | 74.76 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-6.0bpw | 6.0 | 8.0 | 88.81 GB |
| nintwentydo/Pixtral-Large-Instruct-2411-exl2-8.0bpw | 8.0 | 8.0 | 97.51 GB |
- Downloads last month
- 5
Inference API (serverless) has been turned off for this model.
Model tree for nintwentydo/Pixtral-Large-Instruct-2411-exl2-4.5bpw
Base model
mistralai/Pixtral-Large-Instruct-2411