Mistral-Small-24B-Base lineage
According to the model card, the model is an instruction-fine-tuned version of Mistral-Small-24B-Base-2501, with hub tags recording the same base.
Open Source Model Profile · gghfez
Mistral-Small-24B-Instruct-2501
Mistral-Small-24B-Instruct-2501 is a 23.57B-parameter Mistral instruct fine-tune from gghfez. According to the model card, it tunes Mistral-Small-24B-Base-2501 with function calling and system prompts.
- Publisher
- gghfez
- Task
- text-generation
- Model type
- mistral
- License
- apache-2.0
- Library
- vllm
- Publication status
- Accepted · not indexed
Model overview
Mistral-Small-24B-Instruct-2501 is published by gghfez as a Mistral text-generation model. The captured configuration identifies MistralForCausalLM with model type mistral, and Safetensors metadata reports 23,572,403,200 parameters. According to the model card, it instruction-fine-tunes Mistral-Small-24B-Base-2501 with function calling and system-prompt support, with card data recording apache-2.0.
Recorded capabilities
Documented function calling
According to the model card, the release documents native function calling with JSON output and tool-calling examples via vLLM.
System-prompt instruct template
According to the model card, it supports system prompts and documents a V7-Tekken template with system, user, and assistant placeholders.
vLLM deployment notes
According to the model card, the publisher recommends vLLM for production pipelines and notes about 55GB GPU RAM for bf16 or fp16 operation, with over 60GB noted in another example.
Use cases in the source record
- Fast-response conversational assistants and low-latency function-calling workflows using the documented vLLM tool-call setup.
- System-prompted local inference experiments using the documented V7-Tekken instruct template.
- Self-hosted deployment trials following the publisher-documented vLLM and Transformers loading patterns.
Limitations and unknowns
- No evaluation results or context-window value were extracted.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
- No pricing or current availability figures were extracted.
Source and provenance
Source: gghfez/Mistral-Small-24B-Instruct-2501
Captured: Unknown. Processed: 2026-09-07T19:35:22.053588+00:00.
Re-Uploaded without consolidated weights Model Card for Mistral-Small-24B-Instruct-2501 Mistral Small 3 ( 2501 ) sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models! This model is an instruction-fine-tuned version of the base model: Mistral-Small-24B-Base-2501 . Mistral Small can be deployed locally and is exceptionally "knowledge-dense", fitting in a single RTX 4090 or a 32GB RAM MacBook once quantized. Perfect for: Fast response conversational agents. Low latency function calling. Subject matter experts via fin…
F001F002F003F004F005F006F007F009F010F012F014F016F018F020F021F022F024F026F032