---
title: "Mistral 7B as a Local Voice Agent | Micdrop"
description: "Mistral 7B tested as the agent of a local call, compared with Qwen3 4B Instruct, the recommended model."
url: "https://micdrop.dev/docs/local-models/explorations/mistral-7b"
---

# Mistral 7B as a Local Voice Agent

Tested as the agent, because French projects often ask for a Mistral model. Few Mistral models fit a personal computer. Mistral Small 4 is a mixture of experts with 119 billion parameters, Mistral Medium and Large are larger, and the only open weights that fit are Mistral 7B, last updated in 2024.

Like the other agents in this section, it was compared with the recommended model, [Qwen3 4B Instruct](/docs/local-models/agent), using `ollama-agent.ts`: the same four turns, the same prompt with the automatic prompts on, the same machine, and each model loaded before its run. The runs were done in French and in English.

Turn

Mistral 7B v0.3

Qwen3 4B, recommended

A greeting

First token after 0.1 to 0.3 s, 3 to 7 s of text

First token after ~145 ms, a short answer

Asking the time, with a `get_time` tool

No call, an invented time, ~3 s to the first token

Tool called, the real time, 1.1 to 1.3 s

A meaningless `"euh"` or `"uh"`

Answered every time

Skipped 3 times out of 4

`"Merci, au revoir !"`

Thanked the user for “the instructions”

Said goodbye without ending the call

Ollama lists `tools` among the capabilities of this model, but it never produced a valid tool call with the long system prompt Micdrop builds. It made up the time instead, 13 h 15 when it was almost midnight. It also treats the automatic prompts as user messages, so it answers a goodbye by thanking the user for “the detailed instructions”.

After the greeting, every turn takes about 3 seconds to start, which is already the time budget of a whole spoken turn. Use Qwen3 4B Instruct, or the Mistral API if you need a Mistral model.
