ME

Messier One

MessierGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters4.96B
Context256K
Layers33
Architectureqwen35
Smallest quant2.2 GB
Quick answer

Messier One needs about 4.7 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.2 GB (Q2_K) to 9.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Messier One – a decision model that outputs probabilities for multiple-choice queries

Messier One is a 4.96B parameter Qwen35-based model fine‑tuned for decision tasks. It reads a state and typed questions and returns calibrated probabilities for each option. The model does not generate text and is served via a simple POST endpoint.

Good at

  • Fast single‑pass decisions
  • High accuracy on up to 255 options
  • Calibrated probability outputs

Limits

  • No text generation
  • No vision support
  • Requires 8‑k context for memory estimates

Best for

  • Tool routing decisions
  • Category selection from large lists
  • Goal‑driven answer calibration

Who it’s for. Developers building decision‑making services that need quick, probabilistic outputs without text generation. Suitable for server‑side inference where a single forward pass is sufficient.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.2 GB 3.8 GB
Fits Get file →
Q3_K_S2.4 GB 4.0 GB
Fits Get file →
Q3_K_M2.6 GB 4.2 GB
Fits Get file →
Q3_K_L2.8 GB 4.4 GB
Fits Get file →
IQ4_XS2.9 GB 4.5 GB
Fits Get file →
Q4_K_S3.0 GB 4.6 GB
Fits Get file →
Q4_K_M3.1 GB 4.7 GB
Fits Get file →
Q5_K_S3.5 GB 5.1 GB
Fits Get file →
Q5_K_M3.6 GB 5.2 GB
Fits Get file →
Q6_K4.1 GB 5.7 GB
Fits Get file →
Q8_05.3 GB 6.9 GB
Fits Get file →
F169.9 GB 11.5 GB
Too big Get file →

For 8‑GB VRAM use Q2_K (file size 2.17 GB, estimated 3.8 GB memory). With 16‑GB VRAM Q4_K_M (3.14 GB, 4.7 GB memory) is a good balance. For 24‑GB VRAM the full 5.29 GB Q8_0 (6.9 GB memory) offers higher precision.

What GPU do you need for Messier One?

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 Q3_K_S (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.3 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.9 GB file, about 11.5 GB in use).

Which Messier One quant should you choose?

Q4_K_M is the usual starting point for Messier One: it balances file size and quality well. Here it is a 3.1 GB file.

The Q8_0 file is 5.3 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 Q2_K at 2.2 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

Architectureqwen35
Parameters4.96B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bymradermacher
FamilyMessier
Downloads (HF)182
Last updated2026-10-07

Frequently asked questions about Messier One

How much VRAM does Messier One need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.1 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 Messier One on an 8 GB GPU?

Yes, with Q8_0: the 5.3 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Messier One GGUF?

It depends on the quant: Q2_K is 2.2 GB, Q3_K_S is 2.4 GB, Q3_K_M is 2.6 GB, Q3_K_L is 2.8 GB, IQ4_XS is 2.9 GB, Q4_K_S is 3.0 GB and 6 more.

What context length does Messier One support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Messier One GGUF?

The files are on Hugging Face in the mradermacher/messier-one-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 Messier One use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Messier One on 8 GB VRAM?

Yes, the Q2_K quant requires about 3.8 GB memory at 8‑k context, fitting within 8 GB VRAM.

Does Messier One support vision tasks?

No, the model does not include vision capabilities.

What license applies to Messier One?

The model is licensed under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Messier models

All Messier →

Other small models

All small models →