Language

Ornith 1.0 35B (MoE)

Deep Reinforce Ornith 1.0 35B — agentic-coding MoE with 256 routed experts, 8 selected per token and 1 shared, over 40 layers. 256K context, vision input via the bundled projector. Designed for single-GPU deployment.

MITSource verified

Specification

Model ID

ornith-1.0-35b

Family

ornith

Modality

Language

Parameters

35B (MoE, 3B active)

Context

262,144 tokens

Quantization

UD-Q4_K_XL

Weights

20.8 GB

Minimum RAM

26 GB

Source

Weights and provenance.

Repository

unsloth/Ornith-1.0-35B-GGUF

Registry license

MIT

Source license

mit

Access

Open — weights fetch without accepting additional terms.

Serve it

# Pull the weights onto a node
tenzro model download ornith-1.0-35b

# Serve it
tenzro model serve ornith-1.0-35b

# 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":"ornith-1.0-35b"}]}'

Same family

Ornith 1.0 397B (MoE)

397B (MoE, 17B active)

Ornith 1.0 9B

← All models