MI

Harbinger-24B

MistralGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant6.5 GB
Quick answer

Harbinger-24B 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 29 quants, from 6.5 GB (IQ1_S) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Harbinger-24B – a 24.6‑billion‑parameter instruction‑tuned LLM

Harbinger-24B is a 23.6‑billion‑parameter model based on Mistral‑Small‑3.1‑24B‑Instruct‑2503. It supports long‑context inference up to 131072 tokens and is available in a variety of GGUF quantizations. The model is released under the apache‑2.0 license.

Good at

  • Long‑context text generation
  • Instruction following
  • Role‑play

Limits

  • No vision support in this GGUF build
  • Requires large VRAM for higher‑bit quantizations
  • License is apache‑2.0

Best for

  • Local conversational agents
  • Function‑calling workflows
  • Fine‑tuning for niche domains

Who it’s for. Developers and researchers who need a large, instruction‑tuned model that can run locally on consumer GPUs. The model is suitable for applications that require long‑context reasoning and role‑play capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S6.5 GB 8.4 GB
Too big Get file →
IQ1_M7.0 GB 8.9 GB
Too big Get file →
IQ2_XXS7.4 GB 9.2 GB
Too big Get file →
IQ2_XS8.0 GB 9.8 GB
Too big Get file →
IQ2_S8.2 GB 10.1 GB
Too big Get file →
Q2_K_S8.4 GB 10.2 GB
Too big Get file →
IQ2_M8.7 GB 10.5 GB
Too big Get file →
Q2_K_M9.1 GB 11.0 GB
Too big Get file →
IQ3_XXS9.5 GB 11.4 GB
Too big Get file →
IQ3_XS10.0 GB 11.8 GB
Too big Get file →
IQ3_S10.5 GB 12.3 GB
Too big Get file →
IQ3_M10.6 GB 12.5 GB
Too big Get file →
Q3_K_S10.6 GB 12.5 GB
Too big Get file →
Q3_K_M11.6 GB 13.5 GB
Too big Get file →
IQ4_XS12.8 GB 14.6 GB
Too big Get file →
Q4_013.3 GB 15.1 GB
Too big Get file →
IQ4_NL13.5 GB 15.3 GB
Too big Get file →
Q4_K_S13.8 GB 15.7 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q4_114.7 GB 16.6 GB
Too big Get file →
Q5_016.2 GB 18.1 GB
Too big Get file →
Q5_K_S16.6 GB 18.4 GB
Too big Get file →
Q5_K_M16.9 GB 18.7 GB
Too big Get file →
Q5_117.7 GB 19.5 GB
Too big Get file →
Q6_K_M19.3 GB 21.2 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →
BF1633.6 GB 35.4 GB
Too big Get file →
F1633.6 GB 35.4 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.52 GB) or IQ1_M (7.05 GB). For 12 GB VRAM, Q4_K_M (14.34 GB) is a good balance of size and precision. For 24 GB VRAM, Q8_0 (25.05 GB) offers the highest fidelity. Memory estimates are approximate and based on 8 k context.

What GPU do you need for Harbinger-24B?

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 (10.0 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_M (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 BF16 (33.6 GB file, about 35.4 GB in use).

Which Harbinger-24B quant should you choose?

Q4_K_M is the usual starting point for Harbinger-24B: 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 IQ1_S 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 byMungert
FamilyMistral
Licenseapache-2.0
Downloads (HF)616
Last updated2025-09-24

Frequently asked questions about Harbinger-24B

How much VRAM does Harbinger-24B 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 Harbinger-24B 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 Harbinger-24B GGUF?

It depends on the quant: IQ1_S is 6.5 GB, IQ1_M is 7.0 GB, IQ2_XXS is 7.4 GB, IQ2_XS is 8.0 GB, IQ2_S is 8.2 GB, Q2_K_S is 8.4 GB and 23 more.

What context length does Harbinger-24B 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 Harbinger-24B GGUF?

The files are on Hugging Face in the Mungert/Harbinger-24B-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 Harbinger-24B 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 Harbinger-24B on an RTX 4090 with 24 GB VRAM?

Yes, the Q8_0 quantization (25.05 GB) will fit on an RTX 4090, but may require swapping or lower batch sizes.

Does this model support image inputs?

No, the GGUF builds listed do not include vision capabilities.

What license applies to Harbinger-24B?

The model is released under the apache‑2.0 license.

Other GGUFs of Mistral-Small-3.1-24B-Instruct-2503

Similar models

Browse all →

More from Mungert

All by Mungert →

More Mistral models

All Mistral →

Other medium models

All medium models →