Dolphin 2.9.1 Yi 1.5 34B — Hardware Requirements & GPU Compatibility
Chat
Dolphin 2.9.1 Yi 1.5 34B is a 34.4-billion parameter chat model created by Eric Hartford's Dolphin project, fine-tuned from 01.AI's Yi 1.5 34B base. The Dolphin series is known for producing uncensored fine-tunes that remove alignment-based refusals, giving users more direct and unrestricted model responses. This model combines the strong bilingual capabilities of Yi 1.5 with Dolphin's open fine-tuning approach. It requires a GPU with at least 24GB of VRAM for quantized local inference and is popular among users who prefer models without built-in content restrictions.
4.7M downloads
57 likesSpecifications
- Publisher
- dphn
- Family
- Phi
- Parameters
- 34.4B
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 64,000
- Release Date
- 2025-09-08
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Dolphin 2.9.1 Yi 1.5 34B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 69.6 GB | 71.1 GB | 68.78 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Dolphin 2.9.1 Yi 1.5 34B?
BF16 · 69.6 GBDolphin 2.9.1 Yi 1.5 34B (BF16) requires 69.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 91+ GB is recommended. Using the full 8K context window can add up to 1.5 GB, bringing total usage to 71.1 GB. 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?
BF16 · 69.6 GB5 devices with unified memory can run Dolphin 2.9.1 Yi 1.5 34B, 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 need?
Dolphin 2.9.1 Yi 1.5 34B requires 69.6 GB of VRAM at BF16. Full 8K context adds up to 1.5 GB (71.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 34.4B × 16 bits ÷ 8 = 68.8 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.3 GB (at full 8K context)
VRAM usage by quantization
BF1669.6 GBBF16 + full context71.1 GB- Can NVIDIA GeForce RTX 5090 run Dolphin 2.9.1 Yi 1.5 34B?
No — Dolphin 2.9.1 Yi 1.5 34B requires at least 69.6 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 on a Mac?
Dolphin 2.9.1 Yi 1.5 34B requires at least 69.6 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 locally?
Yes — Dolphin 2.9.1 Yi 1.5 34B can run locally on consumer hardware. At BF16 quantization it needs 69.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Dolphin 2.9.1 Yi 1.5 34B?
At BF16, Dolphin 2.9.1 Yi 1.5 34B can reach ~42 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 ÷ 69.6 × 0.55 = ~42 tok/s
Estimated speed at BF16 (69.6 GB)
~42 tok/s~31 tok/s~26 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?
At BF16, the download is about 68.78 GB.
- Which GPUs can run Dolphin 2.9.1 Yi 1.5 34B?
No single consumer GPU has enough VRAM to run Dolphin 2.9.1 Yi 1.5 34B at BF16 (69.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Dolphin 2.9.1 Yi 1.5 34B?
5 devices with unified memory can run Dolphin 2.9.1 Yi 1.5 34B at BF16 (69.6 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.