NCP ArchPreview Dolma3 8.9B Stage2 v3 — Hardware Requirements & GPU Compatibility
Chat
NCP ArchPreview Dolma3 8.9B Stage2 v3 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.
Decent on a 24 GB GPU
Runs on 24 GB (BF16 · ~33 tok/s · 8K)Macs from 24 GB (BF16 · ~11 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run NCP ArchPreview Dolma3 8.9B Stage2 v3
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve ArchSpace-Collection/NCP_ArchPreview_dolma3_8.9B_Stage2_v3 --max-model-len 8192vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 5090 (32 GB) (11 GB headroom) · BF16
- Generation speed
- ~59 tok/s
- generation speed
- Cost per 1M output tokens
- $2.33
- per 1M output tokens
How Much VRAM Does NCP ArchPreview Dolma3 8.9B Stage2 v3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 19.7 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 8K context · ~33 tok/s |
Selected BF16
Brain floating point 1620.8GBat 8K context
- Weights
- 19.0 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 3.2 GB free · ~33 tok/s
≥50 tok/s needs ≥1.51 TB/s · RTX 5090 ~59
Which Hardware Can Run NCP ArchPreview Dolma3 8.9B Stage2 v3?
BF16 · 19.7 GBNCP ArchPreview Dolma3 8.9B Stage2 v3 (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. 122 devices with unified memory can run NCP ArchPreview Dolma3 8.9B Stage2 v3, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
tight · up to 2K ctx
1 GPU
RX 7900 XT~24Simulate output on RX 7900 XT32–40 GB
fits · 11.2 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~59Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.5 9BAlibaba | 99.4 | 6.6 GB | ~103 | same size |
| Granite Switch 4.1 8BIBM | — | 8.4 GB | ~111 | same size |
| Ornith 1.5 9Bornith-ai | — | 6.6 GB | ~103 | same size |
| Apertus V1.5 8Bswiss-ai | — | 8.5 GB | ~111 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| MiniCPM O 4 5OpenBMB | — | 8.3 GB | ~105 | same size |
Specifications
- 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
Frequently Asked Questions
How much VRAM does NCP ArchPreview Dolma3 8.9B Stage2 v3 need?
NCP ArchPreview Dolma3 8.9B Stage2 v3 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can I run NCP ArchPreview Dolma3 8.9B Stage2 v3 on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run NCP ArchPreview Dolma3 8.9B Stage2 v3. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 19.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run NCP ArchPreview Dolma3 8.9B Stage2 v3 locally?
Yes — NCP ArchPreview Dolma3 8.9B Stage2 v3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is NCP ArchPreview Dolma3 8.9B Stage2 v3?
At BF16, NCP ArchPreview Dolma3 8.9B Stage2 v3 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 ÷ 19.6600 × 0.65 = ~264 tok/s
Estimated speed at BF16 (19.7 GB)
Real-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 Stage2 v3?
At BF16, the download is about 17.88 GB.
Which GPUs can run NCP ArchPreview Dolma3 8.9B Stage2 v3?
8 consumer GPUs can run NCP ArchPreview Dolma3 8.9B Stage2 v3 at BF16. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run NCP ArchPreview Dolma3 8.9B Stage2 v3?
122 devices with unified memory can run NCP ArchPreview Dolma3 8.9B Stage2 v3 at BF16 (19.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, 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.