Ornith 1.5 35B A3B REAP 50 NVFP4A16 — Hardware Requirements & GPU Compatibility
ChatCode
Ornith 1.5 35B A3B REAP 50 NVFP4A16 is a 18.5B-parameter open language model from Ttimms in the Ornith family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 37.47 GB of VRAM — see which GPUs and Macs can run it below.
1.1K downloads
3 likesSpecifications
- Publisher
- Ttimms
- Family
- Ornith
- Parameters
- 18.5B
- Architecture
- Qwen3_5MoeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-26
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Ornith 1.5 35B A3B REAP 50 NVFP4A16 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 37.5 GB | 48.1 GB | 37.09 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Ornith 1.5 35B A3B REAP 50 NVFP4A16?
BF16 · 37.5 GBOrnith 1.5 35B A3B REAP 50 NVFP4A16 (BF16) requires 37.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 49+ GB is recommended. Using the full 262K context window can add up to 10.7 GB, bringing total usage to 48.1 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Ornith 1.5 35B A3B REAP 50 NVFP4A16?
BF16 · 37.5 GB27 devices with unified memory can run Ornith 1.5 35B A3B REAP 50 NVFP4A16, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Pro 16" M4 Max (48 GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does Ornith 1.5 35B A3B REAP 50 NVFP4A16 need?
Ornith 1.5 35B A3B REAP 50 NVFP4A16 requires 37.5 GB of VRAM at BF16. Full 262K context adds up to 10.7 GB (48.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 18.5B × 16 bits ÷ 8 = 37.1 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
BF1637.5 GBBF16 + full context48.1 GB- Can NVIDIA GeForce RTX 5090 run Ornith 1.5 35B A3B REAP 50 NVFP4A16?
No — Ornith 1.5 35B A3B REAP 50 NVFP4A16 requires at least 37.5 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Ornith 1.5 35B A3B REAP 50 NVFP4A16 on a Mac?
Ornith 1.5 35B A3B REAP 50 NVFP4A16 requires at least 37.5 GB at BF16, 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 35B A3B REAP 50 NVFP4A16 locally?
Yes — Ornith 1.5 35B A3B REAP 50 NVFP4A16 can run locally on consumer hardware. At BF16 quantization it needs 37.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Ornith 1.5 35B A3B REAP 50 NVFP4A16?
At BF16, Ornith 1.5 35B A3B REAP 50 NVFP4A16 can reach ~128 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 B200 → 8000 ÷ 37.5 × 0.65 = ~139 tok/s
Estimated speed at BF16 (37.5 GB)
~139 tok/s~139 tok/s~128 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 35B A3B REAP 50 NVFP4A16?
At BF16, the download is about 37.09 GB.
- Which GPUs can run Ornith 1.5 35B A3B REAP 50 NVFP4A16?
No single consumer GPU has enough VRAM to run Ornith 1.5 35B A3B REAP 50 NVFP4A16 at BF16 (37.5 GB). Multi-GPU or professional hardware is required.
- Which devices can run Ornith 1.5 35B A3B REAP 50 NVFP4A16?
27 devices with unified memory can run Ornith 1.5 35B A3B REAP 50 NVFP4A16 at BF16 (37.5 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.