Tenzro
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
8B
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
Source license
other
Access
Open — weights fetch without accepting additional terms.

The registry records this model as NVIDIA Open Model License while the source repository states other. Both are shown here rather than one being preferred. Treat the stricter of the two as binding until the discrepancy is resolved upstream.

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