Ornith 1.5 397B — Hardware Requirements & GPU Compatibility
Chat
Ornith-1.5-397B is the flagship model in Ornith AI's Ornith-1.5 family, a roughly 403-billion-parameter Mixture-of-Experts model built for agentic coding. It extends the earlier Ornith-1.0 line, developed on top of Qwen3.5 and Gemma 4, by widening its self-improvement loop to jointly optimize task generation, agent scaffolding, and solution rollouts through reinforcement learning rather than relying on fixed, human-curated training tasks. It supports a 262,144-token context window and is released under the MIT license. At this scale, 4-bit quantization needs roughly 232GB of memory, putting local use firmly in server or multi-GPU territory; most users will rely on a hosted endpoint.
594.1K downloads
89 likesSpecifications
- Publisher
- ornith-ai
- Family
- Ornith
- Parameters
- 403.4B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-18
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Ornith 1.5 397B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 171.9 GB | 187.8 GB | 171.44 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 176.9 GB | 192.9 GB | 176.49 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 197.1 GB | 213.1 GB | 196.66 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 202.1 GB | 218.1 GB | 201.70 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 242.5 GB | 258.4 GB | 242.04 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 287.9 GB | 303.8 GB | 287.42 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 333.2 GB | 349.2 GB | 332.80 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 403.8 GB | 419.8 GB | 403.40 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Ornith 1.5 397B?
Q4_K_M · 242.5 GBOrnith 1.5 397B (Q4_K_M) requires 242.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 316+ GB is recommended. Using the full 262K context window can add up to 16.0 GB, bringing total usage to 258.4 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Ornith 1.5 397B?
Q4_K_M · 242.5 GB3 devices with unified memory can run Ornith 1.5 397B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Ornith 1.5 397B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Ornith 1.5 397B need?
Ornith 1.5 397B requires 242.5 GB of VRAM at Q4_K_M, or 807.2 GB at BF16. Full 262K context adds up to 16.0 GB (258.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 403.4B × 4.8 bits ÷ 8 = 242 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 16.4 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M242.5 GBQ4_K_M + full context258.4 GB- Can NVIDIA GeForce RTX 5090 run Ornith 1.5 397B?
No — Ornith 1.5 397B requires at least 111.4 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Ornith 1.5 397B?
For Ornith 1.5 397B, Q4_K_M (242.5 GB) offers the best balance of quality and VRAM usage. Q5_K_S (277.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 111.4 GB.
VRAM requirement by quantization
IQ2_XXS111.4 GBIQ3_XS166.8 GBQ3_K_L207.2 GBQ4_K_M ★242.5 GBQ5_K_S277.8 GBBF16807.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Ornith 1.5 397B on a Mac?
Ornith 1.5 397B requires at least 111.4 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Ornith 1.5 397B locally?
Yes — Ornith 1.5 397B can run locally on consumer hardware. At Q4_K_M quantization it needs 242.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Ornith 1.5 397B?
At Q4_K_M, Ornith 1.5 397B can reach ~66 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B300 → 8000 ÷ 242.5 × 0.65 = ~163 tok/s
Estimated speed at Q4_K_M (242.5 GB)
~163 tok/s~66 tok/s~66 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Ornith 1.5 397B?
At Q4_K_M, the download is about 242.04 GB. The full-precision BF16 version is 806.80 GB. The smallest option (IQ2_XXS) is 110.93 GB.
- Which GPUs can run Ornith 1.5 397B?
No single consumer GPU has enough VRAM to run Ornith 1.5 397B at Q4_K_M (242.5 GB). Multi-GPU or professional hardware is required.
- Which devices can run Ornith 1.5 397B?
4 devices with unified memory can run Ornith 1.5 397B at Q4_K_M (242.5 GB), including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.