Skip to content

Text model · Ornith

OR Ornith 1.5 35B-A3B: RAM and VRAM requirements

Ornith 1.5 35B-A3B needs about 22.4 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~20.22 GB to download; KV cache and overhead add the rest), or about 37.4 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 4090 (24GB).

Ornith family · 35B params (Mixture-of-Experts: activates only 3B of 35B params per token, so generation is faster than the total size suggests) · released Aug 2026 · 124.2K Ollama pulls.

Shopping for hardware? See what runs Ornith 1.5 35B-A3B →

License MIT · Commercial OK ↓ 291.1K/mo ♥ 559 on HuggingFace
Q4_K_M GGUF
20.22 GB
Q8_0 GGUF
35.21 GB
Memory @ Q4 (4k)
~22.4 GB
Context
256 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Ornith 1.5 35B-A3B runs on 12 of 43 tracked devices at Q4_K_M.

9 run well 3 tight fit 31 too small
Fit check Q4_K_M
No, not enough memory
needs 22.4 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)20.22 GB
+
KV cache (4k)1.4 GB
+
Overhead0.8 GB
=
Total22.4 GB

How context length changes it

4k context ~22.4 GB 32k context ~32.4 GB 128k context ~66.4 GB

Longer context grows the KV cache, which for Ornith 1.5 35B-A3B is sized by its 3B active params, not the full 35B. It needs ~22.4 GB at 4k and ~66.4 GB at 128k.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 14.7 GB est
Q3_K_M 17.1 GB est
Q4_K_M (default) 20.22 GB
Q5_K_M 24.9 GB est
Q6_K 28.7 GB est
Q8_0 35.21 GB
FP16 71.97 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run ornith-1.5:35b
llama.cpp
$ llama-cli -hf ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
LM Studio
$ lms get ornith-ai/Ornith-1.5-35B-A3B-GGUF

Which devices can run Ornith 1.5 35B-A3B?

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Ornith 1.5 35B-A3B need?

At Q4_K_M, Ornith 1.5 35B-A3B needs about 22.4 GB (weights ~20.22 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~37.4 GB.

What is the Q4_K_M GGUF file size of Ornith 1.5 35B-A3B?

The Q4_K_M GGUF file is about 20.22 GB to download, and the Q8_0 GGUF is about 35.21 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~22.4 GB of memory at Q4_K_M.

Can Ornith 1.5 35B-A3B run on a laptop?

Ornith 1.5 35B-A3B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Is Ornith 1.5 35B-A3B cheaper to run because it is a MoE model?

It is faster, not lighter. Ornith 1.5 35B-A3B activates only 3B of 35B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 35B.

Can I use Ornith 1.5 35B-A3B commercially?

Yes. Ornith 1.5 35B-A3B is licensed MIT, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Ornith 1.5 35B-A3B's memory and quant figures.

MoE: ~35B total / ~3B active (256 experts, 8 per token) on the Qwen3.5-MoE architecture, vision-capable, 256K context, MIT. Vendor GGUF sizes; the card's ~70GB bf16 figure matches the 71.97GB sum. Fast on unified memory thanks to the 3B active params. The 397B sibling is deferred until its active-param count is published.

Sources

Last validated 2026-09-07. Memory figures are estimates. See methodology.