Model Type |
| |
Additional Notes |
| |
Supported Languages |
|
LLM Name | Mixtral 8x7B V0.1 |
Repository ๐ค | https://huggingface.co/mistralai/Mixtral-8x7B-v0.1 |
Model Size | 46.7b |
Required VRAM | 93.6 GB |
Updated | 2025-09-08 |
Maintainer | mistralai |
Model Type | mixtral |
Model Files | |
Supported Languages | fr it de es en |
Gated Model | Yes |
Model Architecture | MixtralForCausalLM |
License | proprietary |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.36.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Mixtral 8x7B V0.1 GGUF | 430 | 5045 | 15 GB |
Mixtral 8x7B V0.1 GPTQ | 127 | 1790 | 23 GB |
...hon Mixtral V1.3.75bpw H6 EXL2 | 3 | 6 | 22 GB |
Mixtral 8x7b V0.1 AWQ | 10 | 1274 | 24 GB |
...Hermes 2 Mixtral 8x7B DPO 4bit | 18 | 224 | 10 GB |
Mixtral 8x7B V0.1 GGUF | 1 | 109 | 17 GB |
...ixtral 8x7B DPO 5.0bpw H6 EXL2 | 6 | 13 | 29 GB |
... 8x7B DPO 3.7bpw H6 EXL2 Rpcal | 4 | 9 | 21 GB |
... 8x7B DPO 5.0bpw H6 EXL2 Rpcal | 1 | 8 | 29 GB |
...ixtral 8x7B SFT 6.0bpw H6 EXL2 | 2 | 8 | 35 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Mixtral 8x7B Instruct V0.1 | 32K / 93.6 GB | 289151 | 4548 |
Nous Hermes 2 Mixtral 8x7B DPO | 32K / 93.6 GB | 11716 | 448 |
GritLM 8x7B KTO | 32K / 93.6 GB | 9797 | 3 |
Sensualize Mixtral Bf16 | 32K / 93.6 GB | 0 | 0 |
Skadi Mixtral V1 | 32K / 93.5 GB | 0 | 0 |
Franziska Mixtral V1 | 32K / 93.5 GB | 0 | 0 |
Typhon Mixtral V1 | 32K / 93.4 GB | 0 | 0 |
Smaug Mixtral V0.1 | 32K / 187.7 GB | 9781 | 12 |
NatureLM 8x7B | 32K / 0.3 GB | 90 | 14 |
Mixtral 8x7B Instruct V0.1 FP8 | 32K / 47.1 GB | 2086 | 0 |
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