---

license: apache-2.0 model_name: Mistral-Nemo-Instruct-2407 base_model: mistralai/Mistral-Nemo-Instruct-2407 inference: false model_creator: mistralai quantized_by: Second State Inc. language: - en - fr - de - es - it - pt - ru - zh - ja

---

---

Mistral-Nemo-Instruct-2407-GGUF

Original Model

mistralai/Mistral-Nemo-Instruct-2407

Run with LlamaEdge

• LlamaEdge version: v0.12.4
• Prompt template

- Prompt type: mistral-instruct

- Prompt string

<s>[INST] {usermessage1} [/INST]{assistantmessage1}</s>[INST] {usermessage2} [/INST]{assistantmessage2}</s>

• Context size: 128000
• Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Nemo-Instruct-2407-Q5KM.gguf \
    llama-api-server.wasm \
    --prompt-template mistral-instruct \
    --ctx-size 128000 \
    --model-name Mistral-Nemo-Instruct-2407

• Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Nemo-Instruct-2407-Q5KM.gguf \
    llama-chat.wasm \
    --prompt-template mistral-instruct \
    --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Mistral-Nemo-Instruct-2407-Q2K.gguf	Q2K	2	4.79 GB	smallest, significant quality loss - not recommended for most purposes
Mistral-Nemo-Instruct-2407-Q3KL.gguf	Q3K_L	3	6.56 GB	small, substantial quality loss
Mistral-Nemo-Instruct-2407-Q3KM.gguf	Q3K_M	3	6.08 GB	very small, high quality loss
Mistral-Nemo-Instruct-2407-Q3KS.gguf	Q3K_S	3	5.53 GB	very small, high quality loss
Mistral-Nemo-Instruct-2407-Q40.gguf	Q40	4	7.07 GB	legacy; small, very high quality loss - prefer using Q3KM
Mistral-Nemo-Instruct-2407-Q4KM.gguf	Q4K_M	4	7.48 GB	medium, balanced quality - recommended
Mistral-Nemo-Instruct-2407-Q4KS.gguf	Q4K_S	4	7.12 GB	small, greater quality loss
Mistral-Nemo-Instruct-2407-Q50.gguf	Q50	5	8.52 GB	legacy; medium, balanced quality - prefer using Q4KM
Mistral-Nemo-Instruct-2407-Q5KM.gguf	Q5K_M	5	8.73 GB	large, very low quality loss - recommended
Mistral-Nemo-Instruct-2407-Q5KS.gguf	Q5K_S	5	8.52 GB	large, low quality loss - recommended
Mistral-Nemo-Instruct-2407-Q6K.gguf	Q6K	6	10.1 GB	very large, extremely low quality loss
Mistral-Nemo-Instruct-2407-Q80.gguf	Q80	8	13.0 GB	very large, extremely low quality loss - not recommended
Mistral-Nemo-Instruct-2407-f16.gguf	f16	16	24.5 GB

Quantized with llama.cpp b3438.