LLM EXPLORER 56,604 MODELS INDEXED

Codex 24B Small 3.2 by Gryphe

By Gryphe · 17 downloads
HF Repo ↗ Copy URL

Codex 24B Small 3.2 is an open-source language model by Gryphe. Features: 24b LLM, VRAM: 47.3GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.19.

  Axolotl Base model:finetune:mistralai/... Base model:mistralai/mistral-s...   Chatml   En   Finetuned   Instruct   Mistral   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Gryphe/Codex-24B-Small-3.2 

Codex 24B Small 3.2 Parameters and Internals

LLM NameCodex 24B Small 3.2
Repository 🤗https://huggingface.co/Gryphe/Codex-24B-Small-3.2 
Base Model(s)  mistralai/Mistral-Small-3.2-24B-Instruct-2506   mistralai/Mistral-Small-3.2-24B-Instruct-2506
Model Size24b
Required VRAM47.3 GB
Updated2026-07-20
MaintainerGryphe
Model Typemistral
Instruction-BasedYes
Model Files  4.8 GB: 1-of-10   4.8 GB: 2-of-10   4.8 GB: 3-of-10   4.9 GB: 4-of-10   4.8 GB: 5-of-10   4.8 GB: 6-of-10   4.9 GB: 7-of-10   4.8 GB: 8-of-10   4.8 GB: 9-of-10   3.9 GB: 10-of-10
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.52.4
Tokenizer ClassLlamaTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Codex 24B Small 3.2

Best Alternatives
Context / RAM
Downloads
Likes
...ral Nemo Instruct 24B Merge V11000K / 24.6 GB90
...all 3.1 24B Instruct 2503 Text128K / 47.3 GB220
Cydonia 24B V4.3128K / 47.3 GB3652138
Slimaki 24B V1.2128K / 47.3 GB286
Neural V1 24B128K / 47.3 GB93
MS3.2 PaintedFantasy V4.1 24B128K / 47.3 GB8018
Cydonia 24B V4.1128K / 47.3 GB216280
Slimaki 24B V1128K / 47.3 GB1510
Asmodeus 24B V1128K / 47.3 GB4012
MS3.2 PaintedFantasy V3 24B128K / 47.3 GB2835
Note: green Score (e.g. "73.2") means that the model is better than Gryphe/Codex-24B-Small-3.2.