Mistral Small
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
4recommend
1warn against
Nov 14, 2025first mention
Jun 16, 2026latest mention
Why people recommend it
“I've found tons of use cases for mistral small as well.”
“So far it's better for equivalent Qwen 3.5 workloads, and much less expensive.”
Show 2 more
“I use mistral-small with batch API and it's probably the best cost-efficient option out there.”
“it does a good enough work”
Caveats and dissent
“MistralSmall4 is too buggy to use”
Often compared with
Threads where it came up
- Mistral Small 4 3 mentions
- item 48561269 1 mention
- Mistral Medium 3.5 1 mention
- Claude Opus 4.7 costs 20–30% more per session 1 mention
- Vitalik Buterin – "My self-sovereign / local / private / secure LLM setup" 1 mention
- Ask HN: What's the current best local/open speech-to-speech setup? 1 mention
Also written as Mistral Small, Mistral Small 3.2. Data: mistral-small.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 10
“mistral-small3.2”
“I've found tons of use cases for mistral small as well.”
“I appreciate the effort behind Qwen 3.6, Gemma 4 and Mistral Small 4”
“MistralSmall4 is too buggy to use”
“So far it's better for equivalent Qwen 3.5 workloads, and much less expensive.”
“I tested the model in an agentic workflow”
“Copying GPT-OSS-120b?”
“For LLM I settled with Mistral-Small-3.2-24B-Instruct-2506-Q4_K_S.gguf”
“I use mistral-small with batch API and it's probably the best cost-efficient option out there.”
“it does a good enough work”