OpenPangu 7B Diffusion DeepDiver — Hardware Requirements & GPU Compatibility
Chat
OpenPangu 7B Diffusion DeepDiver is a 8.0B-parameter open language model from DLLM-Agent. It supports a context window of up to 32,768 tokens. At BF16 it needs about 16.65 GB of VRAM — see which GPUs and Macs can run it below.
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run OpenPangu 7B Diffusion DeepDiver
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve DLLM-Agent/openPangu-7B-Diffusion-DeepDiver --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on Tesla P40 (24 GB) (5 GB headroom) · BF16
- Generation speed
- ~14 tok/s
- generation speed
- Cost per 1M output tokens
- $2.50
- per 1M output tokens
How Much VRAM Does OpenPangu 7B Diffusion DeepDiver Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 16.6 GB | 20.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~39 tok/s |
Selected BF16
Brain floating point 1618.7GBat 16K context
- Weights
- 16.1 GB
- KV cache
- 2.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 5.4 GB free · ~39 tok/s
≥50 tok/s needs ≥1.28 TB/s · RTX 5090 ~70
Which Hardware Can Run OpenPangu 7B Diffusion DeepDiver?
BF16 · 16.6 GBOpenPangu 7B Diffusion DeepDiver (BF16) requires 16.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 33K context window can add up to 4.3 GB, bringing total usage to 20.9 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run OpenPangu 7B Diffusion DeepDiver, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 1.4 GB free · up to 16K ctx
1 GPU
RX 7900 XT~29Simulate output on RX 7900 XT32–40 GB
fits · 13.3 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~70Simulate output on RTX 5090M5 Max36 GB~19Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate 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 |
|---|---|---|---|---|
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Hy MT2 7BTencent | — | 7.3 GB | ~122 | same size |
| Gemma 4 E4BGoogle | — | 5.6 GB | ~123 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
Specifications
- Publisher
- DLLM-Agent
- Parameters
- 8.0B
- Architecture
- PanguEmbeddedForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 153,376
- Release Date
- 2026-03-12
Frequently Asked Questions
How much VRAM does OpenPangu 7B Diffusion DeepDiver need?
OpenPangu 7B Diffusion DeepDiver requires 16.6 GB of VRAM at BF16. Full 33K context adds up to 4.3 GB (20.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.0B × 16 bits ÷ 8 = 16.1 GB
KV Cache + Overhead ≈ 0.5 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.
KV Cache + Overhead ≈ 4.8 GB (at full 33K context)
VRAM usage by quantization
Can I run OpenPangu 7B Diffusion DeepDiver on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run OpenPangu 7B Diffusion DeepDiver. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 16.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run OpenPangu 7B Diffusion DeepDiver locally?
Yes — OpenPangu 7B Diffusion DeepDiver can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is OpenPangu 7B Diffusion DeepDiver?
At BF16, OpenPangu 7B Diffusion DeepDiver can reach ~288 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~39 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 ÷ 16.65 × 0.65 = ~312 tok/s
Estimated speed at BF16 (16.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of OpenPangu 7B Diffusion DeepDiver?
At BF16, the download is about 16.06 GB.
Which GPUs can run OpenPangu 7B Diffusion DeepDiver?
8 consumer GPUs can run OpenPangu 7B Diffusion DeepDiver 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 OpenPangu 7B Diffusion DeepDiver?
122 devices with unified memory can run OpenPangu 7B Diffusion DeepDiver at BF16 (16.6 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.