Sage-A1.5 needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 0.4 GB to 21.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Sage‑A1.5: 37B Mixture‑of‑Experts model for long‑horizon scientific problem solving
Sage‑A1.5 is a 37 billion‑parameter Mixture‑of‑Experts model based on the qwen35moe architecture. It supports 262,144‑token context and is licensed under Apache‑2.0. The model is designed for agentic orchestration, verification, and open scientific discovery.
Good at
- Agentic orchestration of parallel sub‑tasks
- Self‑verification and strategy revision
- Exploratory scientific research
Limits
- Requires 8‑k context for memory estimates
- Large VRAM needed for full‑precision or high‑bit quantizations
- No vision support in the base GGUF files
Best for
- Long‑horizon scientific problem solving
- Agent‑based task decomposition
- Research workflow automation
Who it’s for. Researchers and developers needing a large‑scale agentic model for complex, multi‑step tasks. The model is suitable for building scientific discovery pipelines and advanced AI agents.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 1.6 GB | Fits | Get file → | |
| IQ3_S | 16.1 GB | 17.2 GB | Too big | Get file → | |
| Q3_K | 16.1 GB | 17.2 GB | Too big | Get file → | |
| IQ3_S | 17.5 GB | 18.7 GB | Too big | Get file → | |
| Q3_K | 17.5 GB | 18.7 GB | Too big | Get file → | |
| IQ4_XS | 19.3 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (19.32 GB file, ~20.5 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (21.71 GB file, ~22.9 GB memory) offers the best balance of size and quality. Larger VRAM allows use of the 16‑GB IQ3_S or Q3_K files for higher fidelity.
What GPU do you need for Sage-A1.5?
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 (0.4 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
Which Sage-A1.5 quant should you choose?
Q4_K_M is the usual starting point for Sage-A1.5: it balances file size and quality well. Here it is a 21.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.4 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 Sage-A1.5
How much VRAM does Sage-A1.5 need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 Sage-A1.5 on an 8 GB GPU?
Yes, with the smaller files: the 0.4 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sage-A1.5 GGUF?
It depends on the quant: file is 0.4 GB, IQ3_S is 16.1 GB, Q3_K is 16.1 GB, IQ3_S is 17.5 GB, Q3_K is 17.5 GB, IQ4_XS is 19.3 GB and 1 more.
What context length does Sage-A1.5 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Sage-A1.5 GGUF?
The files are on Hugging Face in the na0x2c6/Sage-A1.5-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 Sage-A1.5 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 Sage‑A1.5 on 8 GB VRAM?
Use the IQ4_XS quantization; it requires about 20.5 GB memory at 8k context, which exceeds 8 GB VRAM, so it is not feasible without further compression.
Does Sage‑A1.5 support image input?
The base GGUF files do not include vision support. Use the separate vision projector file from the official repo for image input.
What license applies to Sage‑A1.5?
The model is released under the Apache‑2.0 license.