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.
Decent on a 24 GB GPU
Runs from 12 GB (IQ2_XXS · 8K)Best on 24 GB (Q4_K_M · ~31 tok/s · 8K)Macs from 16 GB (IQ2_XXS · ~14 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Dolphin 2.9.1 Yi 1.5 34B
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
ollama run hf.co/mradermacher/dolphin-2.9.1-yi-1.5-34b-i1-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 1.0 GB free · 8K context
Download: dolphin-2.9.1-yi-1.5-34b.i1-Q4_K_M.gguf20.66 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 32 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 5090 (32 GB) (9 GB headroom) · Q4_K_M
- Generation speed
- ~54 tok/s
- generation speed
- Cost per 1M output tokens
- $2.54
- per 1M output tokens
How Much VRAM Does Dolphin 2.9.1 Yi 1.5 34B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.4 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~43 tok/s | |
| 15.8 GB | — | 3-bit small — 3-bit small quantization | Fits: 8K context · ~41 tok/s | |
| 17.6 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~37 tok/s | |
| 18 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 8K context · ~36 tok/s | |
| 21.4 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~31 tok/s | |
| 25.3 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 25.3 GB | |
| 29.2 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.2 GB | |
| 35.2 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35.2 GB |
Selected Q4_K_M
4-bit medium quantization23.0GBat 8K context
- Weights
- 20.6 GB
- KV cache
- 2.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 1.1 GB free · ~31 tok/s
≥50 tok/s needs ≥1.65 TB/s · RTX 5090 ~54
Or .
Which Hardware Can Run Dolphin 2.9.1 Yi 1.5 34B?
Q4_K_M · 21.4 GBDolphin 2.9.1 Yi 1.5 34B (Q4_K_M) requires 21.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 8K context window can add up to 1.5 GB, bringing total usage to 22.9 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run Dolphin 2.9.1 Yi 1.5 34B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q3_K_L (19.9 GB)
1 GPU
RX 7900 XT~26Simulate output on RX 7900 XT32–40 GB
fits · 9.1 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~54Simulate output on RTX 5090M5 Max36 GB~15Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~6Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Dolphin 2.9.1 Yi 1.5 34B
Phi family · 9 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | same size |
| Sage A1.5InternScience | — | 22 GB | ~151 | same size |
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
Specifications
- Publisher
- dphn
- Family
- Phi
- Parameters
- 34.4B
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 64,000
- Release Date
- 2024-05-18
- License
- Apache 2.0
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 21.4 GB of VRAM at Q4_K_M, or 69.6 GB at BF16. Full 8K context adds up to 1.5 GB (22.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 34.4B × 4.8 bits ÷ 8 = 20.6 GB
KV Cache + Overhead ≈ 0.8 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.
KV Cache + Overhead ≈ 2.3 GB (at full 8K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Dolphin 2.9.1 Yi 1.5 34B?
Yes, at Q4_K_M (21.4 GB) or lower. Higher quantizations like Q5_K_S (24.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Dolphin 2.9.1 Yi 1.5 34B?
For Dolphin 2.9.1 Yi 1.5 34B, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (24.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Dolphin 2.9.1 Yi 1.5 34B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Dolphin 2.9.1 Yi 1.5 34B, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 21.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
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. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Dolphin 2.9.1 Yi 1.5 34B?
At Q4_K_M, Dolphin 2.9.1 Yi 1.5 34B can reach ~224 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~31 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 ÷ 21.4 × 0.65 = ~243 tok/s
Estimated speed at Q4_K_M (21.4 GB)
Real-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 Q4_K_M, the download is about 20.63 GB. The full-precision BF16 version is 68.78 GB. The smallest option (IQ2_XXS) is 9.46 GB.
Which GPUs can run Dolphin 2.9.1 Yi 1.5 34B?
7 consumer GPUs can run Dolphin 2.9.1 Yi 1.5 34B at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
Which devices can run Dolphin 2.9.1 Yi 1.5 34B?
100 devices with unified memory can run Dolphin 2.9.1 Yi 1.5 34B at Q4_K_M (21.4 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.