metadata

base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
inference: false
language:
  - fr
  - it
  - de
  - es
  - en
license: apache-2.0
model_creator: Mistral AI_
model_name: Mixtral 8X7B Instruct v0.1
model_type: mixtral
pipeline_tag: text-generation
quantized_by: Second State Inc.

Mixtral-8x7B-Instruct-v0.1-GGUF

Original Model

mistralai/Mixtral-8x7B-Instruct-v0.1

Run with LlamaEdge

LlamaEdge version: v0.2.8 and above

Prompt template

Prompt type: mistral-instruct

Prompt string

<s> [INST] {user_message_1} [/INST] {assitant_message_1}</s> [INST] {user_message_2} [/INST]

Context size: 4096

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mixtral-8x7B-Instruct-v0.1-Q5_K_M.gguf llama-api-server.wasm -p mistral-instruct

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mixtral-8x7B-Instruct-v0.1-Q5_K_M.gguf llama-chat.wasm -p mistral-instruct

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Mixtral-8x7B-Instruct-v0.1-Q2_K.gguf	Q2_K	2	17.3 GB	smallest, significant quality loss - not recommended for most purposes
Mixtral-8x7B-Instruct-v0.1-Q3_K_L.gguf	Q3_K_L	3	24.2 GB	small, substantial quality loss
Mixtral-8x7B-Instruct-v0.1-Q3_K_M.gguf	Q3_K_M	3	22.5 GB	very small, high quality loss
Mixtral-8x7B-Instruct-v0.1-Q3_K_S.gguf	Q3_K_S	3	20.4 GB	very small, high quality loss
Mixtral-8x7B-Instruct-v0.1-Q4_0.gguf	Q4_0	4	26.4 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Mixtral-8x7B-Instruct-v0.1-Q4_K_M.gguf	Q4_K_M	4	28.4 GB	medium, balanced quality - recommended
Mixtral-8x7B-Instruct-v0.1-Q4_K_S.gguf	Q4_K_S	4	26.7 GB	small, greater quality loss
Mixtral-8x7B-Instruct-v0.1-Q5_0.gguf	Q5_0	5	32.2 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Mixtral-8x7B-Instruct-v0.1-Q5_K_M.gguf	Q5_K_M	5	33.2 GB	large, very low quality loss - recommended
Mixtral-8x7B-Instruct-v0.1-Q5_K_S.gguf	Q5_K_S	5	32.2 GB	large, low quality loss - recommended
Mixtral-8x7B-Instruct-v0.1-Q6_K.gguf	Q6_K	6	38.4 GB	very large, extremely low quality loss
Mixtral-8x7B-Instruct-v0.1-Q8_0.gguf	Q8_0	8	49.6 GB	very large, extremely low quality loss - not recommended