Yes — with 159.9 GB to spare
Ornith 1.5 397B-A17B at Q4_K_M fits your M3 Ultra · 512 GB entirely in unified memory at 8K context, at an estimated 22 tokens per second. There is room for its full 256K window.
The flagship Ornith on the Qwen3.5 397B-A17B architecture, MIT-licensed. A 256 GB Mac Studio at Q4, and it is in the Ollama library.
Hardware requirements What hardware do I need to run Ornith 1.5 397B-A17B? →At Q4_K_M with an 8K context: a 512 GB Mac (M3 Ultra). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 392.8 GB | 393.7 GB | — | ~12 | −0.1% ppl | 9.7 GB over |
| Q6_K | 303.2 GB | 304.0 GB | 256K | 16 | −0.4% ppl | Long context |
| Q5_K_M | 262.0 GB | 262.9 GB | 256K | 19 | −0.8% ppl | Long context |
| Q4_K_M | 223.2 GB | 224.1 GB | 256K | 22 | −1.9% ppl | Recommended |
| Q3_K_M | 180.7 GB | 181.5 GB | 256K | 27 | −5.4% ppl | Long context |
| Q2_K | 154.8 GB | 155.7 GB | 256K | 31 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 15 of its 60 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/Ornith-1.5-397B-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M3 Ultra · 512 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ornith 1.5 35B-A3B 35.9B MoE · same family |
Q4_K_M · 20.9 GB | 112 | Runs great |
| Ornith 1.5 9B 9.41B · same family |
Q4_K_M · 6.1 GB | 84 | Runs great |
| Qwen3.5 397B-A17B 403B MoE · similar size |
Q4_K_M · 227.4 GB | 22 | Runs great |
| GLM-5.3-Flash 320B-A18B 321B MoE · similar size |
Q4_K_M · 181.2 GB | 21 | Runs great |
| DeepSeek V4.1 Flash 552B-A16B 552B MoE · similar size |
Q4_K_M · 311.0 GB | 23 | Runs great |
| DeepSeek V4 Flash 284B-A13B 284B MoE · similar size |
Q4_K_M · 160.7 GB | 29 | Runs great |
| Qwen3 235B-A22B 235B MoE · similar size |
Q4_K_M · 134.2 GB | 17 | Runs great |
Ornith 1.5 397B-A17B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
224.1 GB | — | Won't fit |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
224.1 GB | — | Won't fit |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
224.1 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
224.1 GB | — | Won't fit |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
224.1 GB | — | Won't fit |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
224.1 GB | — | Won't fit |