CO

Codex 24B Small 3.2

CodexGGUF by bartowskiUpdated 2025-06-22
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant6.5 GB
Quick answer

Codex 24B Small 3.2 needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 6.5 GB (IQ2_XXS) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Codex 24B Small 3.2 – a roleplay‑focused text‑only LLM

Codex 24B Small 3.2 is a 23.6 billion‑parameter llama‑style model trained on 39 million tokens of curated roleplay and instruction data. It focuses on diverse storytelling and does not include vision. The model is released under apache‑2.0.

Good at

  • Roleplay with varied dialogue patterns
  • Instruction following with GPT‑4.1 style clarity
  • Narrative generation in second‑person present tense

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Large VRAM needed for higher‑quality quants

Best for

  • Interactive text adventures
  • Creative writing assistants
  • Character dialogue generators

Who it’s for. Developers and hobbyists who need a text‑only LLM for roleplay or narrative tasks. The model is suitable for projects that can handle the memory demands of large quants and do not require image or multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS6.5 GB 8.4 GB
Too big Get file →
IQ2_XS7.2 GB 9.0 GB
Too big Get file →
IQ2_S7.5 GB 9.3 GB
Too big Get file →
IQ2_M8.1 GB 10.0 GB
Too big Get file →
Q2_K8.9 GB 10.7 GB
Too big Get file →
IQ3_XXS9.3 GB 11.1 GB
Too big Get file →
Q2_K_L9.5 GB 11.4 GB
Too big Get file →
IQ3_XS9.9 GB 11.7 GB
Too big Get file →
Q3_K_S10.4 GB 12.2 GB
Too big Get file →
IQ3_M10.7 GB 12.5 GB
Too big Get file →
Q3_K_M11.5 GB 13.3 GB
Too big Get file →
Q3_K_L12.4 GB 14.2 GB
Too big Get file →
IQ4_XS12.8 GB 14.6 GB
Too big Get file →
Q3_K_XL13.0 GB 14.8 GB
Too big Get file →
IQ4_NL13.5 GB 15.3 GB
Too big Get file →
Q4_013.5 GB 15.3 GB
Too big Get file →
Q4_K_S13.5 GB 15.4 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q4_K_L14.8 GB 16.7 GB
Too big Get file →
Q4_114.9 GB 16.7 GB
Too big Get file →
Q5_K_S16.3 GB 18.1 GB
Too big Get file →
Q5_K_M16.8 GB 18.6 GB
Too big Get file →
Q5_K_L17.2 GB 19.0 GB
Too big Get file →
Q6_K19.3 GB 21.2 GB
Too big Get file →
Q6_K_L19.7 GB 21.5 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (7.21 GB file, 9 GB memory). For 12 GB VRAM, IQ3_S (10.4 GB file, 12.2 GB memory) is a good balance. For 16 GB VRAM or more, Q4_K_M (14.33 GB file, 16.2 GB memory) offers higher quality. Estimates are approximate.

What GPU do you need for Codex 24B Small 3.2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ3_XS (9.9 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_L (19.7 GB file, about 21.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).

Which Codex 24B Small 3.2 quant should you choose?

Q4_K_M is the usual starting point for Codex 24B Small 3.2: it balances file size and quality well. Here it is a 14.3 GB file.

The Q8_0 file is 25.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 6.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bybartowski
FamilyCodex
Licenseapache-2.0
Downloads (HF)3,213
Last updated2025-06-22

Frequently asked questions about Codex 24B Small 3.2

How much VRAM does Codex 24B Small 3.2 need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Codex 24B Small 3.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Codex 24B Small 3.2 GGUF?

It depends on the quant: IQ2_XXS is 6.5 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB, IQ2_M is 8.1 GB, Q2_K is 8.9 GB, IQ3_XXS is 9.3 GB and 21 more.

What context length does Codex 24B Small 3.2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Codex 24B Small 3.2 GGUF?

The files are on Hugging Face in the bartowski/Gryphe_Codex-24B-Small-3.2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Codex 24B Small 3.2 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Codex 24B Small 3.2 on 8 GB VRAM?

Yes, the IQ2_XS quant uses 7.21 GB file size and requires about 9 GB memory at 8 k context. It is the smallest quant that fits within 8 GB VRAM.

Does this model support image input?

No. The model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Codex-24B-Small-3.2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Codex models

All Codex →

Other medium models

All medium models →