dlasher/ Devstral-Small-2-24B-Instruct-2512:IQ4_NL

3 1 week ago

pulled as BF16, requant to IQ4_NL (combined_en_huge) -- (English + Coding focus)

vision 
ollama run dlasher/Devstral-Small-2-24B-Instruct-2512:IQ4_NL

Details

1 week ago

21963087ed9a · 14GB

model
mistral3
·
23.6B
·
IQ4_NL
projector
clip
·
439M
·
BF16
params
{ "min_p": 0.05, "num_batch": 2048, "num_ctx": 262144, "presence_penalty": 0, "r
template
{{- if .System }}<|im_start|>system {{ .System }}<|im_end|> {{- end }} {{- range .Messages }} {{- if

Readme

==================================================
 PERPLEXITY QUALITY SCORECARD
 Base Model PPL      : 5.2987 (16-bit reference)
 Quantized Model PPL : 5.4030 (IQ4_NL target)
 Perplexity Drift    : +0.1043 (+1.97%)
 Quality Assessment  : [PASS] EXCELLENT (Near-Lossless / Gold Standard)
==================================================

Devstral Small 2 24B Instruct 2512 Devstral is an agentic LLM for software engineering tasks. Devstral Small 2 excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.

This model is an Instruct model in FP8, fine-tuned to follow instructions, making it ideal for chat, agentic and instruction based tasks for SWE use cases.

For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we invite companies to reach out to us.

Key Features The Devstral Small 2 Instruct model offers the following capabilities:

Agentic Coding: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents. Lightweight: with its compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an appropriate model for local deployment and on-device use. Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes. Context Window: A 256k context window. Updates compared to Devstral Small 1.1:

Vision Capabilities: Enables the model to analyze images and provide insights based on visual content, in addition to text. Improved Performance: Devstral Small 2 is a step-up compared to its predecessors. Attention Softmax Temperature: Devstral Small 2 uses the same architecture as Ministral 3 using rope-scaling as introduced by Llama 4 and Scalable-Softmax Is Superior for Attention. Better Generalization: Generalises better to diverse prompts and coding environments. Use Cases AI Code Assistants, Agentic Coding, and Software Engineering Tasks. Leveraging advanced AI capabilities for complex tool integration and deep codebase understanding in coding environments.

SOURCES: