Ornith 1.0 9B

At the default Q4_K_M, 114 of 151 phones have enough estimated usable memory; 98 also reach 3+ tokens/s. On Mac, 52 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
9B
Family
ornith
Released
2026-06
Tags
coding · chat · reasoning

Downloads & memory by quant

The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.

QuantDownloadMemory neededPhone reality
Q4_K_M ★5.6 GB~7.1 GB114 memory-fit · 98 usable
Q5_K_M6.5 GB~8.1 GB111 memory-fit · 95 usable
Q6_K7.4 GB~9 GB111 memory-fit · 95 usable
Q8_09.5 GB~11.2 GB67 memory-fit · 67 usable

Ornith 1.0 9B at Q4_K_M on 151 phones

This table is fixed to the recommended Q4_K_M, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.

PhoneChip · RAMNeedsSpeedVerdict

~ = bandwidth-based estimate · ✓ = measured on real hardware

Ornith 1.0 9B on 54 Mac configurations

Each Mac uses the recommended Q4_K_M at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict

FAQ

How much RAM do I need to run Ornith 1.0 9B on a phone?

At Q4_K_M, Ornith 1.0 9B needs ~7.1GB of usable memory (weights + KV cache + runtime). In practice that means a 12GB+ Android phone or a 12GB+ iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does Ornith 1.0 9B run on a flagship phone?

On the Xiaomi 18 Fold (Xiaomi XRING O3) it runs at ~9.1 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run Ornith 1.0 9B?

Yes — the iPhone Air runs it at ~6.2 tokens/s at Q4_K_M, using 7.1GB of its ~7.8GB usable memory.

What is the best quantization of Ornith 1.0 9B for mobile?

Q4_K_M (5.6GB download) is the size/quality sweet spot of the 4 quants available. Total memory needed is ~7.1GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run Ornith 1.0 9B?

114 of the 151 phones we track have enough estimated usable memory at Q4_K_M; 98 also reach our usable-speed threshold of 3 tokens/s, and 1 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run Ornith 1.0 9B?

52 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_K_M when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.

What is Ornith 1.0 9B good for on a phone?

It's tagged for coding, chat, reasoning. At 9B parameters, it balances quality and speed for daily use.

Guides for Ornith

Can Your Phone Run Ornith 1.0 9B? The Coding Model Everyone's Running Locally

Similar models

Ornith 1.0 35B-A3Bgrug 9B (ProCreations)Ornith 1.0 397BQwen 3.5 9BQwythos 9B v2