LLM EXPLORER 59,420 MODELS INDEXED

Devstral 2 123B Instruct 2512 by BrainForge

By BrainForge · 30 downloads

Devstral 2 123B Instruct 2512 is an open-source language model by BrainForge. Features: 123b LLM, VRAM: 69.6GB, Context: 256K, Instruction-Based, LLM Explorer Score: 0.23.

  4-bit   Gptq   Instruct   Ministral3   Region:us   Safetensors   Sharded   Tensorflow

Devstral 2 123B Instruct 2512 Parameters and Internals

LLM NameDevstral 2 123B Instruct 2512
Repository πŸ€—https://huggingface.co/BrainForge/Devstral-2-123B-Instruct-2512 
Model Size123b
Required VRAM69.6 GB
Updated2026-08-25
MaintainerBrainForge
Model Typeministral3
Instruction-BasedYes
Model Files  5.2 GB: 1-of-14   5.2 GB: 2-of-14   5.2 GB: 3-of-14   5.3 GB: 4-of-14   5.3 GB: 5-of-14   5.2 GB: 6-of-14   5.3 GB: 7-of-14   5.3 GB: 8-of-14   5.2 GB: 9-of-14   5.3 GB: 10-of-14   5.3 GB: 11-of-14   5.2 GB: 12-of-14   3.4 GB: 13-of-14   3.2 GB: 14-of-14
Model ArchitectureMinistral3ForCausalLM
Context Length262144
Model Max Length262144
Transformers Version5.3.0
Tokenizer ClassTokenizersBackend
Padding Token<pad>
Vocabulary Size131072
Torch Data Typefloat16

Best Alternatives to Devstral 2 123B Instruct 2512

Best Alternatives
Context / RAM
Downloads
Likes
Devstral 2 123B Instruct 2512256K / 196.3 GB57919329
...tral 2 123B Instruct 2512 4bit256K / 70 GB2301
...tral 2 123B Instruct 2512 8bit256K / 133 GB1161
Note: green Score (e.g. "73.2") means that the model is better than BrainForge/Devstral-2-123B-Instruct-2512.