Language

NVIDIA Cosmos-Reason2 8B (video reasoning VLM)

NVIDIA Cosmos-Reason2 8B — video reasoning VLM for Physical AI, post-trained on Qwen3-VL-8B-Instruct. Takes video or images plus text and answers in text, with spatial-temporal understanding and object detection. 256K context. Needs the mmproj projector for the vision path; NVIDIA's own repo is gated and requires HF_TOKEN, this GGUF conversion is not.

NVIDIA Open Model LicenseSource verified

Specification

Model ID

cosmos-reason2-8b

Family

cosmos-reason

Modality

Language

Parameters

Context

262,144 tokens

Quantization

Q4_K_M

Weights

4.7 GB

Minimum RAM

8 GB

Source

Weights and provenance.

Repository

mradermacher/Cosmos-Reason2-8B-GGUF

Registry license

NVIDIA Open Model License

Access

Open — weights fetch without accepting additional terms.

The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.

Serve it

# Pull the weights onto a node
tenzro model download cosmos-reason2-8b

# Serve it
tenzro model serve cosmos-reason2-8b

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"cosmos-reason2-8b"}]}'

← All models