D1 2B — Hardware Requirements & GPU Compatibility
VisionFunctions
d1-2B is a decision model from Liquid AI for text, pictures, and video, built on LFM3-VL-2B and about 1.9 billion parameters in size. Instead of generating tokens, it returns calibrated, typed answers with their probabilities in a single forward pass, and it can answer any number of named questions about one input in a single call. It handles classification, extraction of text, numbers, and dates with their spans, locating objects in pictures, and estimating quantities with an interval. The publisher reports 5.7 ms per decision on an NVIDIA H100. Context length is 128K tokens. It is released under the LFM Open License v1.0, a custom license whose terms are in the repository, and was published in October 2026. It is a specialized classifier-style model rather than a chat model, and at under 2 billion parameters it runs easily on a laptop or any consumer GPU.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 125K)Best on 24 GB (Q4_K_M · ~423 tok/s · 125K)Macs from 8 GB (Q4_K_M · ~46 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run D1 2B
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/LiquidAI/d1-2B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 21.7 GB free · 16K context
Download: d1-2B-Q4_K_M.gguf1.10 GBLiquidAI
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~151 tok/s
- generation speed
- Cost per 1M output tokens
- $0.11
- per 1M output tokens
How Much VRAM Does D1 2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.2 GB | 2.7 GB | 3-bit · i-quant small — Importance-weighted 3-bit, small | Fits: 125K context · ~537 tok/s | |
| 1.2 GB | 2.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 125K context · ~537 tok/s | |
| 1.3 GB | 2.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 125K context · ~489 tok/s | |
| 1.4 GB | 2.9 GB | 4-bit · i-quant compact — Importance-weighted 4-bit, compact | Fits: 125K context · ~458 tok/s | |
| 1.6 GB | 3.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 125K context · ~423 tok/s | |
| 1.8 GB | 3.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 125K context · ~370 tok/s | |
| 2.0 GB | 3.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 125K context · ~331 tok/s | |
| 2.3 GB | 3.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 125K context · ~282 tok/s | |
| 4.2 GB | 5.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 125K context · ~155 tok/s |
Selected Q4_K_M
4-bit medium quantization2.3GBat 16K context
- Weights
- 1.2 GB
- KV cache
- 0.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.8 GB free · ~423 tok/s
≥50 tok/s needs ≥119 GB/s · RTX 5090 ~752, RTX 3090 Ti ~423
Which Hardware Can Run D1 2B?
Q4_K_M · 1.6 GBD1 2B (Q4_K_M) requires 1.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 128K context window can add up to 6.2 GB, bringing total usage to 7.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run D1 2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.8 GB free · up to 125K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~319Simulate output on RTX 3080RTX 2080 Ti~258Simulate output on RTX 2080 TiRTX 3070 Ti~255Simulate output on RTX 3070 TiM3*8 GB~46Simulate output on iMac 24" M3 (8 GB)Orin Nano~43Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~31Simulate output on iPhone 1720 GB
fits · 17.8 GB free · up to 125K ctx
1 GPU
RX 7900 XT~310Simulate output on RX 7900 XT32–40 GB
fits · 29.8 GB free · up to 125K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~752Simulate output on RTX 5090M5 Max36 GB~208Simulate output on Mac Studio M5 Max (36 GB)M532 GB~69Simulate output on MacBook Air 13" M5 (32 GB)Orin~86Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~57Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen 1 8BAlibaba | — | 1.9 GB | ~542 | same size |
| Gemma 3n E2B IT Litert LmGoogle | — | 3.1 GB | ~496 | same size |
| Qwen3 1.7BAlibaba | — | 3.4 GB | ~374 | same size |
| DeepSeek R1 Distill Qwen 1.5BDeepSeek | — | 1.8 GB | ~461 | same size |
| MiniCPM 2B Sft BF16OpenBMB | — | 3 GB | ~291 | same size |
| Nemotron Labs Audex 2BNVIDIA | — | 6.1 GB | ~149 | same size |
Specifications
- Publisher
- Liquid AI
- Parameters
- 1.9B
- Architecture
- D1Model
- Context Length
- 128,000 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-10-24
- License
- Other
Frequently Asked Questions
How much VRAM does D1 2B need?
D1 2B requires 1.6 GB of VRAM at Q4_K_M, or 4.2 GB at BF16. Full 128K context adds up to 6.2 GB (7.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.9B × 4.8 bits ÷ 8 = 1.2 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 ≈ 6.5 GB (at full 128K context)
VRAM usage by quantization
What's the best quantization for D1 2B?
For D1 2B, Q4_K_M (1.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.8 GB) provides better quality if you have the VRAM. The smallest option is IQ3_S at 1.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run D1 2B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run D1 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run D1 2B locally?
Yes — D1 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is D1 2B?
At Q4_K_M, D1 2B can reach ~3097 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~423 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 ÷ 1.55 × 0.65 = ~3355 tok/s
Estimated speed at Q4_K_M (1.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of D1 2B?
At Q4_K_M, the download is about 1.15 GB. The full-precision BF16 version is 3.84 GB. The smallest option (IQ3_S) is 0.82 GB.
Which GPUs can run D1 2B?
52 consumer GPUs can run D1 2B 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 D1 2B?
163 devices with unified memory can run D1 2B at Q4_K_M (1.6 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.