Dolphin 2.9.1 Yi 1.5 34B GGUF — Hardware Requirements & GPU Compatibility
Chat
88 downloads
1 likesSpecifications
- Publisher
- mradermacher
- Family
- Phi
- Parameters
- 34B
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Dolphin 2.9.1 Yi 1.5 34B GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 74.8 GB | — | 68.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Dolphin 2.9.1 Yi 1.5 34B GGUF?
BF16 · 74.8 GBDolphin 2.9.1 Yi 1.5 34B GGUF (BF16) requires 74.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 98+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Dolphin 2.9.1 Yi 1.5 34B GGUF?
BF16 · 74.8 GB5 devices with unified memory can run Dolphin 2.9.1 Yi 1.5 34B GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Related Models
Frequently Asked Questions
- How much VRAM does Dolphin 2.9.1 Yi 1.5 34B GGUF need?
Dolphin 2.9.1 Yi 1.5 34B GGUF requires 74.8 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 34B × 16 bits ÷ 8 = 68 GB
KV Cache + Overhead ≈ 6.8 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1674.8 GB- Can NVIDIA GeForce RTX 5090 run Dolphin 2.9.1 Yi 1.5 34B GGUF?
No — Dolphin 2.9.1 Yi 1.5 34B GGUF requires at least 74.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Dolphin 2.9.1 Yi 1.5 34B GGUF on a Mac?
Dolphin 2.9.1 Yi 1.5 34B GGUF requires at least 74.8 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 Dolphin 2.9.1 Yi 1.5 34B GGUF locally?
Yes — Dolphin 2.9.1 Yi 1.5 34B GGUF can run locally on consumer hardware. At BF16 quantization it needs 74.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Dolphin 2.9.1 Yi 1.5 34B GGUF?
At BF16, Dolphin 2.9.1 Yi 1.5 34B GGUF can reach ~39 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 74.8 × 0.55 = ~39 tok/s
Estimated speed at BF16 (74.8 GB)
AMD Instinct MI300X~39 tok/sNVIDIA H100 SXM~29 tok/sAMD Instinct MI250X~24 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Dolphin 2.9.1 Yi 1.5 34B GGUF?
At BF16, the download is about 68.00 GB.
- Which GPUs can run Dolphin 2.9.1 Yi 1.5 34B GGUF?
No single consumer GPU has enough VRAM to run Dolphin 2.9.1 Yi 1.5 34B GGUF at BF16 (74.8 GB). Multi-GPU or professional hardware is required.
- Which devices can run Dolphin 2.9.1 Yi 1.5 34B GGUF?
5 devices with unified memory can run Dolphin 2.9.1 Yi 1.5 34B GGUF at BF16 (74.8 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), NVIDIA DGX A100 640GB. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.