SP

SPES 9B

SpesGGUF by mradermacherUpdated 2026-05-08
Download on Hugging Face
Parameters9.43B
Context4K
Layers28
Architectureqwen3moe
Smallest quant3.7 GB
Quick answer

SPES 9B needs about 7.3 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.7 GB (Q2_K) to 18.9 GB (F16).

SPES 9B – a 9B‑parameter Mixture‑of‑Experts language model

SPES 9B is a 9B‑parameter MoE model based on the Qwen3moe architecture. It was pretrained with the SPES framework, which reduces memory usage during decentralized training. The model supports tool usage and is released under Apache‑2.0.

Good at

  • Tool‑based task execution
  • Decentralized training research
  • MoE inference

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Large VRAM needed for higher quants

Best for

  • Research on MoE training
  • Evaluating decentralized LLMs
  • Tool‑enabled inference

Who it’s for. Researchers and developers interested in Mixture‑of‑Experts models and decentralized training paradigms. The model is suitable for those who need a memory‑efficient large language model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.7 GB 4.6 GB
Fits Get file →
Q3_K_S4.3 GB 5.3 GB
Fits Get file →
Q3_K_M4.7 GB 5.6 GB
Fits Get file →
Q3_K_L5.0 GB 6.0 GB
Fits Get file →
IQ4_XS5.2 GB 6.2 GB
Fits Get file →
Q4_K_S5.5 GB 6.5 GB
Fits Get file →
Q4_K_M5.8 GB 6.8 GB
Fits Get file →
Q5_K_S6.6 GB 7.5 GB
Tight Get file →
Q5_K_M6.8 GB 7.7 GB
Tight Get file →
Q6_K7.8 GB 8.7 GB
Too big Get file →
Q8_010.0 GB 11.0 GB
Too big Get file →
F1618.9 GB 19.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 5.5 GB, estimated 6.9 GB memory). For 12 GB VRAM, Q5_K_S (6.58 GB, 8 GB memory) is a good balance. For 20 GB VRAM, Q8_0 (10.03 GB, 11.5 GB memory) offers higher precision.

What GPU do you need for SPES 9B?

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 Q3_K_S (4.3 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.6 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 11.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (18.9 GB file, about 20.3 GB in use).

Which SPES 9B quant should you choose?

Q4_K_M is the usual starting point for SPES 9B: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 10.0 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 Q2_K at 3.7 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

Architectureqwen3moe
Parameters9.43B (approximate, mixture of experts)
Layers28
Trained context4,096 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilySpes
Base modelzjr2000/SPES-9B
Licenseapache-2.0
Downloads (HF)731
Last updated2026-05-08

Frequently asked questions about SPES 9B

How much VRAM does SPES 9B need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.8 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 SPES 9B on an 8 GB GPU?

Yes, with Q5_K_S: the 6.6 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 SPES 9B GGUF?

It depends on the quant: Q2_K is 3.7 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.7 GB, Q3_K_L is 5.0 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.5 GB and 6 more.

What context length does SPES 9B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.5 GB at 4K.

Where can I download SPES 9B GGUF?

The files are on Hugging Face in the mradermacher/SPES-9B-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 SPES 9B 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 SPES 9B on 8 GB VRAM?

Yes, using the Q4_K_S quant, which requires approximately 6.9 GB of VRAM at 8 k context.

Does SPES 9B support vision tasks?

No, the model has no vision capabilities.

What license applies to SPES 9B?

The model is released under the Apache‑2.0 license.

Other GGUFs of SPES-9B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Spes models

All Spes →

Other small models

All small models →