novaforgeai/
novaforge-mistral:7b-q3km

31 13 hours ago

Quantized Mistral 7B Instruct models optimized for fast, CPU-only local inference with Ollama. Multiple variants balancing speed, quality, and memory efficiency.

... /
template
c502cd931388 · 218B
[INST] {{ range $index, $_ := .Messages }}
{{- if eq .Role "system" }}{{ .Content }}
{{ else if eq .Role "user" }}{{ .Content }}[/INST]
{{- else if eq .Role "assistant" }} {{ .Content }}</s>[INST] {{ end }}
{{- end }}