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 →
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.
Memory breakdown
How context length changes it
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
| 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 run ornith-1.5:35b llama-cli -hf ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M lms get ornith-ai/Ornith-1.5-35B-A3B-GGUF Which devices can run Ornith 1.5 35B-A3B?
NVIDIA GPUs
- Nvidia GeForce RTX 2060 (6GB) No
- Nvidia GeForce RTX 3060 Ti (8GB) No
- Nvidia GeForce GTX 1070 (8GB) No
- Nvidia GeForce RTX 3060 (12GB) No
- Nvidia GeForce RTX 4070 (12GB) No
- Nvidia GeForce RTX 4060 Ti (16GB) No
- Nvidia GeForce RTX 4080 (16GB) No
- Nvidia GeForce RTX 4090 (24GB) Tight
- Nvidia GeForce RTX 3090 (24GB) Tight
- Nvidia GeForce RTX 5090 (32GB) Yes
Apple Silicon Macs
- Apple M1 (8GB) No
- Apple M2 (16GB) No
- Apple M4 (16GB) No
- Apple M5 (16GB) No
- Apple M3 Pro (18GB) No
- Apple M4 (24GB) No
- Apple M4 Pro (24GB) No
- Apple M5 (32GB) No
- Apple M4 Pro (48GB) Yes
- Apple M5 Pro (48GB) Yes
- Apple M4 Max (64GB) Yes
- Apple M4 Max (128GB) Yes
- Apple M5 Max (128GB) Yes
- Apple M3 Ultra (256GB) Yes
RAM-only laptops
iPhone & iPad
Android
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.