KA

KAL 24B Mx v1

KalGGUF by mradermacherUpdated 2025-12-06
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant0.0 GB
Quick answer

KAL 24B Mx v1 needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.0 GB to 18.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

KAL 24B Mx v1 – 22.2B‑parameter LLM for Mexican Spanish

KAL 24B Mx v1 is a 22.2‑billion‑parameter LLM based on the Mistral architecture. It is fine‑tuned with LoRA adapters for Mexican Spanish and is ready for inference without external adapters. The model supports a 32,768‑token context window and is released under Apache 2.0.

Good at

  • Mexican Spanish conversational AI
  • Legal and bureaucratic Q&A
  • Content generation for Mexican context

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No external adapters needed

Best for

  • Chatbots for Mexican Spanish
  • Legal document drafting
  • RAG‑enhanced Q&A systems

Who it’s for. Developers building Spanish‑Mexico focused chatbots or content tools. Researchers needing a ready‑to‑use LLM for local language tasks. Enterprises requiring a licensed, open‑source model for compliance and localization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.4 GB
Fits Get file →
IQ1_S4.8 GB 7.2 GB
Tight Get file →
IQ1_M5.3 GB 7.6 GB
Tight Get file →
IQ2_XXS6.0 GB 8.4 GB
Too big Get file →
IQ2_XS6.6 GB 9.0 GB
Too big Get file →
IQ2_S7.0 GB 9.4 GB
Too big Get file →
IQ2_M7.6 GB 10.0 GB
Too big Get file →
Q2_K_S7.7 GB 10.0 GB
Too big Get file →
Q2_K8.3 GB 10.7 GB
Too big Get file →
IQ3_XXS8.6 GB 11.0 GB
Too big Get file →
IQ3_XS9.2 GB 11.6 GB
Too big Get file →
Q3_K_S9.6 GB 12.0 GB
Too big Get file →
IQ3_S9.7 GB 12.1 GB
Too big Get file →
IQ3_M10.1 GB 12.4 GB
Too big Get file →
Q3_K_M10.8 GB 13.1 GB
Too big Get file →
Q3_K_L11.7 GB 14.1 GB
Too big Get file →
IQ4_XS11.9 GB 14.3 GB
Too big Get file →
Q4_012.6 GB 15.0 GB
Too big Get file →
Q4_K_S12.7 GB 15.0 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q4_113.9 GB 16.3 GB
Too big Get file →
Q5_K_S15.3 GB 17.7 GB
Too big Get file →
Q5_K_M15.7 GB 18.1 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (4.83 GB, 7.2 GB memory) or IQ1_M (5.27 GB, 7.6 GB memory). With 12‑GB VRAM, Q4_0 (12.61 GB, 15 GB memory) or Q4_K_M (13.34 GB, 15.7 GB memory) are suitable. For 20‑GB VRAM, Q6_K (18.25 GB, 20.6 GB memory) fits well. Estimates are approximate.

What GPU do you need for KAL 24B Mx v1?

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: the best quant that fits is the main file (0.0 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.4 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_M (5.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_S (9.6 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).

Which KAL 24B Mx v1 quant should you choose?

Q4_K_M is the usual starting point for KAL 24B Mx v1: it balances file size and quality well. Here it is a 13.3 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyKal
Licenseapache-2.0
Downloads (HF)718
Last updated2025-12-06

Frequently asked questions about KAL 24B Mx v1

How much VRAM does KAL 24B Mx v1 need?

About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 KAL 24B Mx v1 on an 8 GB GPU?

Yes, with IQ1_M: the 5.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KAL 24B Mx v1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.0 GB, IQ2_XS is 6.6 GB, IQ2_S is 7.0 GB and 18 more.

What context length does KAL 24B Mx v1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download KAL 24B Mx v1 GGUF?

The files are on Hugging Face in the mradermacher/KAL-24B-mx-v1-i1-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 KAL 24B Mx v1 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 KAL 24B Mx v1 on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quantized files which require about 7.2–7.6 GB of VRAM at 8‑k context.

Does this model support image inputs?

No, the model has no vision capabilities.

Other GGUFs of KAL-24B-mx-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kal models

All Kal →

Other medium models

All medium models →