Dolphin X1 Trinity Nano — Hardware Requirements & GPU Compatibility
Chat
Dolphin X1 Trinity Nano is a 6.1B-parameter open language model from dphn in the Phi family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 4.09 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 64K)Best on 24 GB (Q4_K_M · ~243 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~48 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Dolphin X1 Trinity Nano
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve dphn/Dolphin-X1-Trinity-Nano --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 RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~167 tok/s
- generation speed
- Cost per 1M output tokens
- $0.14
- per 1M output tokens
How Much VRAM Does Dolphin X1 Trinity Nano Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.0 GB | 4.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~260 tok/s | |
| 3.4 GB | 5.2 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~253 tok/s | |
| 4.1 GB | 5.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~243 tok/s | |
| 4.8 GB | 6.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~233 tok/s | |
| 5.5 GB | 7.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~223 tok/s | |
| 6.5 GB | 8.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~211 tok/s | |
| 12.7 GB | 14.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~158 tok/s |
Selected Q4_K_M
4-bit medium quantization4.9GBat 16K context
- Weights
- 3.7 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.1 GB free · ~243 tok/s
≥50 tok/s needs ≥62 GB/s · RTX 5090 ~273, RTX 3090 Ti ~243
Which Hardware Can Run Dolphin X1 Trinity Nano?
Q4_K_M · 4.1 GBDolphin X1 Trinity Nano (Q4_K_M) requires 4.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. Using the full 131K context window can add up to 7.4 GB, bringing total usage to 11.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Dolphin X1 Trinity Nano, including NVIDIA DGX Spark, NVIDIA Jetson AGX Thor Developer Kit, MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.1 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~224Simulate output on RTX 3080RTX 2080 Ti~209Simulate output on RTX 2080 TiRTX 3070 Ti~208Simulate output on RTX 3070 TiM3*8 GB~48Simulate output on iMac 24" M3 (8 GB)Orin Nano~75Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~39Simulate output on iPhone 1720 GB
fits · 15.1 GB free · up to 128K ctx
1 GPU
RX 7900 XT~79Simulate output on RX 7900 XT32–40 GB
fits · 27.1 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~273Simulate output on RTX 5090M5 Max36 GB~75Simulate output on Mac Studio M5 Max (36 GB)M532 GB~57Simulate output on MacBook Air 13" M5 (32 GB)Orin~122Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~75Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Dolphin X1 Trinity Nano
Phi family · 9 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Yi 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| TLive Omni 4BTaoLiveAIGC | — | 13.3 GB | ~54 | same size |
| Z Image TurboTongyi-MAI | — | 15.9 GB | ~48 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| GPT J 6BEleutherAI | — | 4 GB | ~166 | same size |
Specifications
- Publisher
- dphn
- Family
- Phi
- Parameters
- 6.1B
- Active parameters
- 1B per token
- Architecture
- AfmoeForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 200,192
- Release Date
- 2026-05-29
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Dolphin X1 Trinity Nano need?
Dolphin X1 Trinity Nano requires 4.1 GB of VRAM at Q4_K_M, or 12.7 GB at BF16. Full 131K context adds up to 7.4 GB (11.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 6.1B × 4.8 bits ÷ 8 = 3.7 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 7.8 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Dolphin X1 Trinity Nano?
For Dolphin X1 Trinity Nano, Q4_K_M (4.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (4.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Dolphin X1 Trinity Nano on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Dolphin X1 Trinity Nano. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Dolphin X1 Trinity Nano locally?
Yes — Dolphin X1 Trinity Nano can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Dolphin X1 Trinity Nano?
At Q4_K_M, Dolphin X1 Trinity Nano can reach ~88 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~243 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 0.7 GB active ÷ (8000 × 0.65) = 0.132 ms, plus 56 layers × 0.055 ms = 3.080 ms, so 1000 ÷ 3.212 ms = ~311 tok/s
Estimated speed at Q4_K_M (4.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Dolphin X1 Trinity Nano?
At Q4_K_M, the download is about 3.67 GB. The full-precision BF16 version is 12.24 GB. The smallest option (Q2_K) is 2.60 GB.
Which GPUs can run Dolphin X1 Trinity Nano?
52 consumer GPUs can run Dolphin X1 Trinity Nano at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Dolphin X1 Trinity Nano?
163 devices with unified memory can run Dolphin X1 Trinity Nano at Q4_K_M (4.1 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.