CO

Cosmos Reason2 8b

CosmosGGUF by apolo13xUpdated 2026-02-20
Download on Hugging Face
Parameters8.19B
Context256K
Layers36
Architectureqwen3vl
Smallest quant5.0 GB
Quick answer

Cosmos Reason2 8b needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 5.0 GB (Q4_K_M) to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Cosmos Reason2 8b – 8B parameter VLM for reasoning, tools, and vision

Cosmos Reason2 8b is an 8B-parameter vision‑language model based on Qwen3VL. It supports reasoning, tool use, and vision tasks. The model can handle up to 262144 input tokens and includes a vision encoder kept at F16 precision.

Good at

  • Physical AI reasoning
  • Spatio‑temporal understanding
  • Object detection with 2D/3D localization

Limits

  • No vision support in llama.cpp
  • Large memory requirement for long context
  • License type is other

Best for

  • Robotics planning
  • Video analytics
  • Data curation

Who it’s for. Developers building AI systems that need reasoning and vision capabilities in a single model. Useful for robotics, simulation, and advanced data analysis.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q8_08.7 GB 10.4 GB
Too big Get file →
F1616.4 GB 18.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (5.03 GB, ~6.7 GB memory). For 12 GB VRAM use Q8_0 (8.71 GB, ~10.4 GB memory). For 16 GB VRAM use F16 (16.39 GB, ~18.1 GB memory). Estimates are approximate.

What GPU do you need for Cosmos Reason2 8b?

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: the best quant that fits is Q4_K_M (5.0 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.4 GB file, about 18.1 GB in use).

Which Cosmos Reason2 8b quant should you choose?

Q4_K_M is the usual starting point for Cosmos Reason2 8b: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 8.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vl
Parameters8.19B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byapolo13x
FamilyCosmos
Licenseother
Downloads (HF)653
Last updated2026-02-20

Frequently asked questions about Cosmos Reason2 8b

How much VRAM does Cosmos Reason2 8b need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Cosmos Reason2 8b on an 8 GB GPU?

Yes, with Q4_K_M: the 5.0 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Cosmos Reason2 8b GGUF?

It depends on the quant: Q4_K_M is 5.0 GB, Q8_0 is 8.7 GB, F16 is 16.4 GB.

What context length does Cosmos Reason2 8b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Cosmos Reason2 8b GGUF?

The files are on Hugging Face in the apolo13x/Cosmos-Reason2-8B-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 Cosmos Reason2 8b use?

Hugging Face lists the license as other. 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 Cosmos Reason2 8b on 8 GB VRAM?

Yes, using the Q4_K_M quantization which is 5.03 GB and requires about 6.7 GB of VRAM at 8K context.

Does the model support vision tasks in llama.cpp?

The vision encoder is kept at F16 precision, so vision support is limited in llama.cpp.

What is the maximum context length?

The model supports up to 262144 input tokens for long‑context understanding.

Other GGUFs of Cosmos-Reason2-8B

Similar models

Browse all →

More from apolo13x

All by apolo13x →

More Cosmos models

All Cosmos →

Other small models

All small models →