DI

DictaLM 3.0 24B Thinking

DictalmGGUF by dicta-ilUpdated 2025-12-04
Download on Hugging Face
Parameters23.6B
Context64K
Layers40
Architecturellama
Smallest quant12.8 GB
Quick answer

DictaLM 3.0 24B Thinking 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 7 quants, from 12.8 GB (IQ4_XS) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

DictaLM 3.0 24B Thinking – a 24‑billion‑parameter reasoning chat model

DictaLM 3.0 24B Thinking is a 23.6‑billion‑parameter llama architecture model focused on reasoning and tool‑calling. It is trained on Hebrew and English corpora and available under an Apache‑2.0 license. The model supports a 65280‑token context window.

Good at

  • Reasoning tasks
  • Tool‑calling integration
  • Hebrew language support

Limits

  • No vision support
  • Requires large VRAM for higher precision
  • License allows unlimited use but no redistribution of weights

Best for

  • Complex problem solving
  • Automated workflow integration
  • Hebrew‑centric content generation

Who it’s for. Developers building reasoning‑heavy applications or Hebrew‑focused content systems. Researchers needing a large‑parameter base for fine‑tuning. Teams requiring tool‑calling capabilities in a chat interface.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS12.8 GB 14.6 GB
Too big Get file →
IQ4_NL13.5 GB 15.3 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q5_K_M16.8 GB 18.6 GB
Too big Get file →
Q6_K19.3 GB 21.2 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 IQ4_XS (12.76 GB file, 14.6 GB memory at 8 k context). For 12 GB VRAM IQ4_NL (13.47 GB file, 15.3 GB memory). For 16 GB VRAM Q4_K_M (14.33 GB file, 16.2 GB memory). Higher precision quants need more memory.

What GPU do you need for DictaLM 3.0 24B Thinking?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ4_NL (13.5 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.3 GB file, about 21.2 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 DictaLM 3.0 24B Thinking quant should you choose?

Q4_K_M is the usual starting point for DictaLM 3.0 24B Thinking: 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 IQ4_XS at 12.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context65,280 tokens
KV cache (fp16)160 KB per token

Source

Quantized bydicta-il
FamilyDictalm
Licenseapache-2.0
Downloads (HF)1,184
Last updated2025-12-04

Frequently asked questions about DictaLM 3.0 24B Thinking

How much VRAM does DictaLM 3.0 24B Thinking 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 DictaLM 3.0 24B Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DictaLM 3.0 24B Thinking GGUF?

It depends on the quant: IQ4_XS is 12.8 GB, IQ4_NL is 13.5 GB, Q4_K_M is 14.3 GB, Q5_K_M is 16.8 GB, Q6_K is 19.3 GB, Q8_0 is 25.1 GB and 1 more.

What context length does DictaLM 3.0 24B Thinking support?

The GGUF header lists a trained context length of 65,280 tokens (64K). 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 DictaLM 3.0 24B Thinking GGUF?

The files are on Hugging Face in the dicta-il/DictaLM-3.0-24B-Thinking-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 DictaLM 3.0 24B Thinking 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 DictaLM 3.0 24B Thinking on 8 GB VRAM?

Use the IQ4_XS quant; it requires about 14.6 GB memory at 8 k context, which fits in 8 GB VRAM with swap.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing unlimited use.

Similar models

Browse all →

More from dicta-il

All by dicta-il →

More Dictalm models

All Dictalm →

Other medium models

All medium models →