MA

Marco o1

MarcoGGUF by AlcoftUpdated 2024-12-01
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2
Smallest quant3.0 GB
Quick answer

Marco o1 needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 11 quants, from 3.0 GB (Q2_K) to 15.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Marco o1 – a 7.62B parameter Qwen2 model focused on open‑ended reasoning

Marco o1 is a 7.62B parameter Qwen2 model trained with chain‑of‑thought fine‑tuning, Monte Carlo Tree Search, and reflection mechanisms. It targets complex real‑world problem solving and open‑ended questions. The model is released under the Apache‑2.0 license.

Good at

  • Open‑ended reasoning
  • Complex problem solving
  • Chain‑of‑thought generation

Limits

  • No vision support
  • Large context requires significant VRAM
  • License allows free use but no commercial claims

Best for

  • Research on reasoning models
  • Educational problem‑solving demos
  • Exploratory AI projects

Who it’s for. Researchers and developers interested in advanced reasoning capabilities and open‑ended problem solving. The model is suitable for academic studies and prototype development.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 4.0 GB
Fits Get file →
Q3_K_S3.5 GB 4.5 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q3_K_L4.1 GB 5.1 GB
Fits Get file →
Q4_K_S4.5 GB 5.4 GB
Fits Get file →
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
Q5_K_S5.3 GB 6.3 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q6_K6.3 GB 7.2 GB
Tight Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
—15.2 GB 16.2 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (4.46 GB file, ~5.4 GB VRAM). For 12 GB VRAM use Q5_K_M (5.44 GB file, ~6.4 GB VRAM). For 16 GB VRAM use Q6_K (6.25 GB file, ~7.2 GB VRAM).

What GPU do you need for Marco o1?

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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.2 GB file, about 16.2 GB in use).

Which Marco o1 quant should you choose?

Q4_K_M is the usual starting point for Marco o1: it balances file size and quality well. Here it is a 4.7 GB file.

The Q8_0 file is 8.1 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 3.0 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

Architectureqwen2
Parameters7.62B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byAlcoft
FamilyMarco
Licenseapache-2.0
Downloads (HF)611
Last updated2024-12-01

Frequently asked questions about Marco o1

How much VRAM does Marco o1 need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 Marco o1 on an 8 GB GPU?

Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Marco o1 GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.5 GB, Q3_K_M is 3.8 GB, Q3_K_L is 4.1 GB, Q4_K_S is 4.5 GB, Q4_K_M is 4.7 GB and 5 more.

What context length does Marco o1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Marco o1 GGUF?

The files are on Hugging Face in the Alcoft/Marco-o1-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 Marco o1 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 Marco o1 on 8 GB VRAM?

Yes, the Q4_K_S quantized model is 4.46 GB and requires about 5.4 GB VRAM at 8k context.

Does Marco o1 support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of Marco-o1

Similar models

Browse all →

More from Alcoft

All by Alcoft →

More Marco models

All Marco →

Other small models

All small models →