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 27 quants, from 0.0 GB 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 – multimodal reasoning model
Apriel 1.5 15b Thinker is a 15B parameter multimodal model built on the llama architecture. It supports text and image reasoning and is released under the MIT license. The model is available in multiple GGUF quantizations for different memory budgets.
Good at
- Text reasoning
- Image reasoning
- Mid‑training efficiency
Limits
- No vision SFT or RL training
- Limited to 262400 context tokens
- Requires GPU for inference
Best for
- Enterprise reasoning tasks
- Multimodal content analysis
- Low‑budget inference
Who it’s for. Developers and researchers needing a compact multimodal model that performs well on reasoning benchmarks. The model is suitable for environments with limited GPU memory but sufficient VRAM to load a chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ2_XS | 4.6 GB | 6.7 GB | Fits | Get file → | |
| IQ2_S | 4.8 GB | 6.9 GB | Fits | Get file → | |
| IQ2_M | 5.2 GB | 7.3 GB | Tight | Get file → | |
| Q2_K | 5.6 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XXS | 5.8 GB | 7.9 GB | Tight | Get file → | |
| IQ3_XS | 6.2 GB | 8.3 GB | Too big | Get file → | |
| Q2_K_L | 6.2 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_S | 6.5 GB | 8.6 GB | Too big | Get file → | |
| IQ3_M | 6.7 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_M | 7.1 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_L | 7.7 GB | 9.8 GB | Too big | Get file → | |
| IQ4_XS | 7.9 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_XL | 8.3 GB | 10.4 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 10.4 GB | Too big | Get file → | |
| IQ4_NL | 8.3 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_S | 8.4 GB | 10.5 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 10.9 GB | Too big | Get file → | |
| Q4_1 | 9.2 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_L | 9.3 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_S | 10.0 GB | 12.1 GB | Too big | Get file → | |
| Q5_K_M | 10.3 GB | 12.4 GB | Too big | Get file → | |
| Q5_K_L | 10.7 GB | 12.8 GB | Too big | Get file → | |
| Q6_K | 11.8 GB | 14.0 GB | Too big | Get file → | |
| Q6_K_L | 12.2 GB | 14.3 GB | Too big | Get file → | |
| Q8_0 | 15.3 GB | 17.5 GB | Too big | Get file → | |
| BF16 | 28.9 GB | 31.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (file size 4.56 GB, memory 6.7 GB). For 12 GB VRAM, Q4_K_M (file size 8.79 GB, memory 10.9 GB) is a good balance. For 16 GB VRAM, Q5_K_L (file size 10.68 GB, memory 12.8 GB) offers higher quality.
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: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (5.8 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_L (9.3 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_L (12.2 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.3 GB file, about 17.5 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 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
Source
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 IQ3_XXS: the 5.8 GB file needs about 7.9 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: file is 0.0 GB, IQ2_XS is 4.6 GB, IQ2_S is 4.8 GB, IQ2_M is 5.2 GB, Q2_K is 5.6 GB, IQ3_XXS is 5.8 GB and 21 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 bartowski/ServiceNow-AI_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, the IQ2_XS quantization requires approximately 6.7 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does the model support image input?
Yes, the model includes image reasoning capabilities, but it has not undergone image SFT training.
What license does the model use?
The model is released under the MIT license, allowing free use and modification.