SA

Sage A1.5 Sangreal ICE

SageGGUF by gbuzhfUpdated 2026-10-28
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant12.2 GB
Quick answer

Sage A1.5 Sangreal ICE needs about 20.0 GB of memory at its main file (a 18.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 12.2 GB to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Sage A1.5 Sangreal ICE – 35.5B Qwen35moe with vision, reasoning, and tools

Sage A1.5 Sangreal ICE is a 35.5 billion‑parameter Qwen35moe model. It supports reasoning, tools, and vision. The model is available in several GGUF quantizations, including a Q8_0 variant.

Good at

  • Reasoning
  • Tools integration
  • Vision support

Limits

  • Large context 262144 tokens
  • Requires high VRAM (≈39 GB for Q8_0 at 8 k context)
  • No license information provided

Best for

  • Complex reasoning tasks
  • Tool‑based workflows
  • Vision‑enabled applications

Who it’s for. Developers building advanced LLM applications that need reasoning, tool use, and vision capabilities. Suitable for research and production environments with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.2 GB 13.4 GB
Too big Get file →
—14.8 GB 16.0 GB
Too big Get file →
—18.8 GB 20.0 GB
Too big Get file →
—22.8 GB 24.0 GB
Too big Get file →
—24.8 GB 26.0 GB
Too big Get file →
Q8_037.8 GB 39.0 GB
Too big Get file →

For 8 k context, the Q8_0 file is 37.8 GB and needs about 39 GB of VRAM. Smaller unknown‑quant files range from 12.19 GB to 24.82 GB, requiring roughly 13.4 GB to 26 GB of VRAM. Choose the smallest file that meets your memory budget.

What GPU do you need for Sage A1.5 Sangreal ICE?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (14.8 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (22.8 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (24.8 GB file, about 26.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).

Which Sage A1.5 Sangreal ICE quant should you choose?

If memory is tight, the smallest file is the first one in the table at 12.2 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

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bygbuzhf
FamilySage
Downloads (HF)10,466
Last updated2026-10-28

Frequently asked questions about Sage A1.5 Sangreal ICE

How much VRAM does Sage A1.5 Sangreal ICE need?

About 20.0 GB at its main file with an 8K context window. That is the 18.8 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 Sage A1.5 Sangreal ICE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sage A1.5 Sangreal ICE GGUF?

It depends on the quant: file is 12.2 GB, file is 14.8 GB, file is 18.8 GB, file is 22.8 GB, file is 24.8 GB, Q8_0 is 37.8 GB.

What context length does Sage A1.5 Sangreal ICE 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 Sangreal ICE GGUF?

The files are on Hugging Face in the gbuzhf/Sage-A1.5-Sangreal-ICE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

No, the smallest quant requires at least 13.4 GB of VRAM at 8 k context.

Does the model support vision?

Yes, vision is supported via a separate projector file.

What sampling parameters are recommended?

Use temperature 1.0, top_p 0.95, top_k 20, min_p 0.0, presence_penalty 1.5, repetition_penalty 1.0.

Similar models

Browse all →

More from gbuzhf

All by gbuzhf →

More Sage models

All Sage →

Other large models

All large models →