NCP ArchPreview Dolma3 8.9B Stage1 — Hardware Requirements & GPU Compatibility
Chat
NCP ArchPreview Dolma3 8.9B Stage1 is a 8.9B-parameter open language model from ArchSpace-Collection. It supports a context window of up to 8,192 tokens. At BF16 it needs about 19.66 GB of VRAM — see which GPUs and Macs can run it below.
1.2K downloads
8 likesSpecifications
- Publisher
- ArchSpace-Collection
- Parameters
- 8.9B
- Architecture
- NCPOlmo3ForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 100,278
- Release Date
- 2026-08-27
- License
- Apache 2.0
Get Started
How Much VRAM Does NCP ArchPreview Dolma3 8.9B Stage1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 19.7 GB | — | 17.88 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 NCP ArchPreview Dolma3 8.9B Stage1?
BF16 · 19.7 GBNCP ArchPreview Dolma3 8.9B Stage1 (BF16) requires 19.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run NCP ArchPreview Dolma3 8.9B Stage1?
BF16 · 19.7 GB41 devices with unified memory can run NCP ArchPreview Dolma3 8.9B Stage1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does NCP ArchPreview Dolma3 8.9B Stage1 need?
NCP ArchPreview Dolma3 8.9B Stage1 requires 19.7 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 8.9B × 16 bits ÷ 8 = 17.9 GB
KV Cache + Overhead ≈ 1.8 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1619.7 GB- Can I run NCP ArchPreview Dolma3 8.9B Stage1 on a Mac?
NCP ArchPreview Dolma3 8.9B Stage1 requires at least 19.7 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 NCP ArchPreview Dolma3 8.9B Stage1 locally?
Yes — NCP ArchPreview Dolma3 8.9B Stage1 can run locally on consumer hardware. At BF16 quantization it needs 19.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is NCP ArchPreview Dolma3 8.9B Stage1?
At BF16, NCP ArchPreview Dolma3 8.9B Stage1 can reach ~244 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~33 tok/s. 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 ÷ 19.7 × 0.65 = ~265 tok/s
Estimated speed at BF16 (19.7 GB)
~265 tok/s~33 tok/s~265 tok/s~244 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of NCP ArchPreview Dolma3 8.9B Stage1?
At BF16, the download is about 17.88 GB.
- Which GPUs can run NCP ArchPreview Dolma3 8.9B Stage1?
8 consumer GPUs can run NCP ArchPreview Dolma3 8.9B Stage1 at BF16 (19.7 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run NCP ArchPreview Dolma3 8.9B Stage1?
41 devices with unified memory can run NCP ArchPreview Dolma3 8.9B Stage1 at BF16 (19.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.