other
9B parameters
Commercial OK
Reviewed July 2026

Ornith 1.0 9B

Ornith 1.0 9B is DeepReinforce's agentic-coding model, RL post-trained on Qwen3.5 and Gemma 4 bases and released June 25, 2026 under MIT. It runs a 256K context, and the Q4_K_M build is 5.6GB. The Ollama tag drew 262.9K pulls in its first two weeks.

License: MIT·Released Jun 25, 2026·Context: 262,144 tokens

Overview

Ornith 1.0 9B is DeepReinforce's agentic-coding model, RL post-trained on Qwen3.5 and Gemma 4 bases and released June 25, 2026 under MIT. It runs a 256K context, and the Q4_K_M build is 5.6GB. The Ollama tag drew 262.9K pulls in its first two weeks.

Strengths

  • MIT license with no usage restrictions
  • RL post-training aimed specifically at agentic coding loops
  • 5.6GB Q4_K_M runs on 8GB cards with context headroom

Weaknesses

  • Two weeks of public adoption — 262.9K pulls is early signal, not a track record
  • Coding-specialized post-training; general chat quality unverified at intake
  • New vendor with little independent benchmark coverage so far
BLK · QUALITY BENCHMARKreviewed · raw logs

Reviewed quality benchmarks

First-party rows were run by RunLocalAI; reviewed community rows are labeled in the data. Every row links to the raw test-run log.

BenchmarkQuantRuntime / HardwareScoreRaw log
HumanEval+
tested 2026-07-18
Q4_K_M
ollama-0.32
rtx-3080-16gb-mobile
73.2/100
Gist →

Q4_K_M note:First-party HumanEval+ on RTX 3080 Laptop 16GB via Ollama 0.32. Windows-safe scoring via scripts/evalplus_score_windows.py. July 2026 campaign.

Want to verify? Every row links to its Gist with full stdout and stderr of the run. The runner script is in the public repo (scripts/run-humaneval-plus.ts) — reproducible end-to-end. Browse all coding scores at /benchmarks/coding.

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M5.6 GB7 GB

Get the model

Ollama

One-line install

ollama run ornith:9bRead our Ollama review →

Hardware that runs this

Cards with enough VRAM for at least one quantization of Ornith 1.0 9B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Frequently asked

What's the minimum VRAM to run Ornith 1.0 9B?

7GB of VRAM is enough to run Ornith 1.0 9B at the Q4_K_M quantization (file size 5.6 GB). Higher-quality quantizations need more.

Can I use Ornith 1.0 9B commercially?

Yes — Ornith 1.0 9B ships under the MIT, which permits commercial use. Always read the license text before deployment.

What's the context length of Ornith 1.0 9B?

Ornith 1.0 9B supports a context window of 262,144 tokens (about 262K).

How do I install Ornith 1.0 9B with Ollama?

Run `ollama pull ornith:9b` to download, then `ollama run ornith:9b` to start a chat session. The default quantization is Q4_K_M.

Source: Vendor official documentation

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify Ornith 1.0 9B runs on your specific hardware before committing money.