AP

Apriel-1.5-15B-Thinker

AprielGGUF by unslothUpdated 2025-10-02
Download on Hugging Face
Parameters14.4B
Context256K
Layers48
Architecturellama
Smallest quant3.6 GB
Quick answer

Apriel-1.5-15B-Thinker needs about 10.9 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 26 quants, from 3.6 GB (IQ1_S) to 28.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Apriel-1.5-15B-Thinker: a 15B multimodal reasoning model

Apriel-1.5-15B-Thinker is a 15B parameter multimodal model that supports text and image reasoning. It is trained with mid‑training only and achieves competitive scores on text and image benchmarks. The model is released under the MIT license.

Good at

  • Text reasoning
  • Image reasoning
  • Mid‑training efficiency

Limits

  • No image SFT or RL
  • Requires at least 8k context for full performance
  • Limited to text and image modalities

Best for

  • Enterprise reasoning tasks
  • Multimodal question answering
  • Single‑GPU deployment

Who it’s for. Developers and researchers who need a compact multimodal model with strong reasoning capabilities. The model is suitable for teams with limited GPU resources and who prefer a MIT‑licensed solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.6 GB 5.7 GB
Fits Get file →
IQ1_M3.9 GB 6.0 GB
Fits Get file →
IQ2_XXS4.3 GB 6.4 GB
Fits Get file →
IQ2_M5.2 GB 7.3 GB
Tight Get file →
Q2_K5.6 GB 7.7 GB
Tight Get file →
Q2_K_L5.8 GB 7.9 GB
Tight Get file →
IQ3_XXS5.8 GB 8.0 GB
Tight Get file →
Q2_K_XL5.9 GB 8.0 GB
Tight Get file →
Q3_K_S6.5 GB 8.6 GB
Too big Get file →
Q3_K_M7.1 GB 9.2 GB
Too big Get file →
Q3_K_XL7.4 GB 9.5 GB
Too big Get file →
IQ4_XS7.9 GB 10.0 GB
Too big Get file →
Q4_08.3 GB 10.4 GB
Too big Get file →
IQ4_NL8.3 GB 10.4 GB
Too big Get file →
Q4_K_S8.4 GB 10.5 GB
Too big Get file →
Q4_K_M8.8 GB 10.9 GB
Too big Get file →
Q4_K_XL8.9 GB 11.0 GB
Too big Get file →
Q4_19.2 GB 11.3 GB
Too big Get file →
Q5_K_S10.0 GB 12.1 GB
Too big Get file →
Q5_K_XL10.3 GB 12.4 GB
Too big Get file →
Q5_K_M10.3 GB 12.4 GB
Too big Get file →
Q6_K11.8 GB 14.0 GB
Too big Get file →
Q6_K_XL12.9 GB 15.0 GB
Too big Get file →
Q8_015.3 GB 17.5 GB
Too big Get file →
Q8_K_XL18.0 GB 20.1 GB
Too big Get file →
BF1628.9 GB 31.0 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (3.63 GB, 5.7 GB memory at 8k context) or IQ1_M (3.88 GB, 6 GB). For 16‑GB VRAM, Q4_K_M (8.79 GB, 10.9 GB) or Q5_K_S (10.02 GB, 12.1 GB) provide a good balance of size and performance. Larger quants such as Q8_0 (15.34 GB, 17.5 GB) require more memory but offer higher precision.

What GPU do you need for Apriel-1.5-15B-Thinker?

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: the best quant that fits is IQ1_M (3.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K_XL (5.9 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.2 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_XL (12.9 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_K_XL (18.0 GB file, about 20.1 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (28.9 GB file, about 31.0 GB in use).

Which Apriel-1.5-15B-Thinker quant should you choose?

Q4_K_M is the usual starting point for Apriel-1.5-15B-Thinker: it balances file size and quality well. Here it is a 8.8 GB file.

The Q8_0 file is 15.3 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 3.6 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
Parameters14.4B
Layers48
Trained context262,400 tokens
KV cache (fp16)192 KB per token

Source

Quantized byunsloth
FamilyApriel
Licensemit
Downloads (HF)1,536
Last updated2025-10-02

Frequently asked questions about Apriel-1.5-15B-Thinker

How much VRAM does Apriel-1.5-15B-Thinker need?

About 10.9 GB at Q4_K_M with an 8K context window. That is the 8.8 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 Apriel-1.5-15B-Thinker on an 8 GB GPU?

Yes, with Q2_K_XL: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Apriel-1.5-15B-Thinker GGUF?

It depends on the quant: IQ1_S is 3.6 GB, IQ1_M is 3.9 GB, IQ2_XXS is 4.3 GB, IQ2_M is 5.2 GB, Q2_K is 5.6 GB, Q2_K_L is 5.8 GB and 20 more.

What context length does Apriel-1.5-15B-Thinker support?

The GGUF header lists a trained context length of 262,400 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Apriel-1.5-15B-Thinker GGUF?

The files are on Hugging Face in the unsloth/Apriel-1.5-15b-Thinker-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 Apriel-1.5-15B-Thinker use?

Hugging Face lists the license as mit. 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 Apriel-1.5-15B-Thinker on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantizations, which are 3.63 GB and 3.88 GB respectively and require about 5.7 GB and 6 GB of VRAM at 8k context.

Does the model support vision tasks?

Yes, it includes image reasoning capabilities, but no image SFT or RL has been performed.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of Apriel-1.5-15b-Thinker

Similar models

Browse all →

More from unsloth

All by unsloth →

More Apriel models

All Apriel →

Other medium models

All medium models →