SA

Strata Sage A1.5

SageGGUF by ykaroutUpdated 2026-10-24
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant21.7 GB
Quick answer

Strata 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. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

35B Mixture‑of‑Experts Qwen3.6 model with agentic orchestration

Strata Sage A1.5 is a 35.5B Qwen3.6‑based model that uses a 256‑expert mixture of experts. It is trained on 262144 context tokens and licensed under Apache‑2.0.

Good at

  • Reasoning
  • Tools usage
  • Agentic orchestration

Limits

  • Requires 16 GB VRAM + 64 GB RAM
  • Large model size
  • No vision support

Best for

  • Long‑horizon scientific problem solving
  • Task delegation and parallel sub‑agents
  • Self‑verification and strategy revision

Who it’s for. Developers building agentic systems that need to decompose complex tasks and verify intermediate results. Researchers interested in open scientific discovery and collaborative exploration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.7 GB 22.9 GB
Too big Get file →

The Q4_K_M GGUF file is 21.72 GB and needs about 22.9 GB of VRAM at 8 k context. It fits on a 16 GB card with 64 GB RAM. For lower VRAM budgets, no other quantizations are available in the file list.

What GPU do you need for Strata 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: 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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).

Which Strata Sage A1.5 quant should you choose?

Q4_K_M is the usual starting point for Strata Sage A1.5: it balances file size and quality well. Here it is a 21.7 GB file.

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 byykarout
FamilySage
Licenseapache-2.0
Downloads (HF)3,711
Last updated2026-10-24

Frequently asked questions about Strata Sage A1.5

How much VRAM does Strata 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 Strata Sage A1.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.9 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q4_K_M is 21.7 GB.

What context length does Strata 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 Strata Sage A1.5 GGUF?

The files are on Hugging Face in the ykarout/Strata-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 Strata 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 Strata Sage A1.5 on 8 GB VRAM?

No, the model requires 16 GB VRAM to load the full weights.

Does it work with llama.cpp?

Yes, it runs in llama.cpp as any qwen35moe GGUF.

Is there vision support?

No, the model does not include vision capabilities.

Other GGUFs of Sage-A1.5

Similar models

Browse all →

More from ykarout

All by ykarout →

More Sage models

All Sage →

Other large models

All large models →