Deepseek Vl2 Tiny — Hardware Requirements & GPU Compatibility
Vision
DeepSeek-VL2-Tiny is the smallest in DeepSeek's VL2 series of Mixture-of-Experts vision-language models, with about 3.4 billion total parameters but only roughly 1.2 billion activated per token. It handles vision-language tasks — visual question answering, OCR, document/table/chart understanding, and visual grounding — below the larger VL2-Small and full VL2 variants. Only a fraction of parameters activate per token, so decoding stays fast even though every expert must still be loaded into memory. It is compact enough to run on a single consumer GPU once quantized. Context length is limited to 4,096 tokens. It is released under DeepSeek's own model license, a custom permissive license with an acceptable-use policy rather than a fully open license like MIT or Apache 2.0. Published in December 2024, it pairs a small DeepSeekMoE-3B backbone with a dynamic image-tiling vision encoder.
93.9K downloads
253 likesSpecifications
- Publisher
- DeepSeek
- Family
- DeepSeek
- Parameters
- 3.4B
- Release Date
- 2024-12-13
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Deepseek Vl2 Tiny Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 7.4 GB | — | 6.74 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Deepseek Vl2 Tiny?
BF16 · 7.4 GBDeepseek Vl2 Tiny (BF16) requires 7.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 10+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Deepseek Vl2 Tiny?
BF16 · 7.4 GB55 devices with unified memory can run Deepseek Vl2 Tiny, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Deepseek Vl2 Tiny need?
Deepseek Vl2 Tiny requires 7.4 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 3.4B × 16 bits ÷ 8 = 6.7 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF167.4 GB- Can I run Deepseek Vl2 Tiny on a Mac?
Deepseek Vl2 Tiny requires at least 7.4 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 Deepseek Vl2 Tiny locally?
Yes — Deepseek Vl2 Tiny can run locally on consumer hardware. At BF16 quantization it needs 7.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Deepseek Vl2 Tiny?
At BF16, Deepseek Vl2 Tiny can reach ~99 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~152 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 ÷ 7.4 × 0.65 = ~319 tok/s
Estimated speed at BF16 (7.4 GB)
~319 tok/s~152 tok/s~319 tok/s~290 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Deepseek Vl2 Tiny?
At BF16, the download is about 6.74 GB.
- Which GPUs can run Deepseek Vl2 Tiny?
52 consumer GPUs can run Deepseek Vl2 Tiny at BF16 (7.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 36 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Deepseek Vl2 Tiny?
59 devices with unified memory can run Deepseek Vl2 Tiny at BF16 (7.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.