Architecture
MoE
Released
2024-12-13
Layers
27
KV Heads
16
Head Dim
128
Family
deepseek
Quantization Options
| Quant | Bits | VRAM @ 4K | Quality |
|---|---|---|---|
| Q3_K_M | 4 | 8.3 GB | low |
| Q3_K_L | 4.3 | 8.9 GB | moderate |
| IQ4_XS | 4.46 | 9.2 GB | moderate |
| Q4_K_S | 4.67 | 9.7 GB | moderate |
| Q4_K_M | 4.89 | 10.1 GB | good |
| Q5_K_S | 5.57 | 11.4 GB | good |
| Q5_K_M | 5.7 | 11.7 GB | good |
| Q6_K | 6.56 | 13.4 GB | excellent |
| Q8_0 | 8.5 | 17.2 GB | lossless |
| FP16 | 16 | 31.9 GB | lossless |
Select your GPU above to see speed estimates and compatibility for each quantization.
Ready to run this?Rent by the hour
Rent a GPU and run DeepSeek-VL2 Small 16B now
Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.
Community Ratings
Loading ratings...
Benchmarks (9)
Run this model
>_
Auto-setup with fitmyllm CLI
Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
GPUs that can run this model
At Q4_K_M quantization. Sorted by minimum VRAM.
NVIDIA RTX 2080 Ti
11 GB VRAM • 616 GB/s
NVIDIA
$350
NVIDIA GTX 1080 Ti
11 GB VRAM • 484 GB/s
NVIDIA
$200
NVIDIA GeForce GTX 1080 Ti
11 GB VRAM • 484 GB/s
NVIDIA
NVIDIA GeForce RTX 2080 Ti
11 GB VRAM • 616 GB/s
NVIDIA
$225
NVIDIA RTX 5070
12 GB VRAM • 672 GB/s
NVIDIA
$549
NVIDIA RTX 4070 Ti
12 GB VRAM • 504 GB/s
NVIDIA
$799
NVIDIA RTX 4070 SUPER
12 GB VRAM • 504 GB/s
NVIDIA
$599
NVIDIA RTX 4070
12 GB VRAM • 504 GB/s
NVIDIA
$549
NVIDIA RTX 3080 Ti
12 GB VRAM • 912 GB/s
NVIDIA
$550
NVIDIA RTX 3080 12GB
12 GB VRAM • 912 GB/s
NVIDIA
$599
NVIDIA RTX 3060 12GB
12 GB VRAM • 360 GB/s
NVIDIA
$329
AMD RX 7700 XT
12 GB VRAM • 432 GB/s
AMD
$449
AMD RX 6700 XT
12 GB VRAM • 384 GB/s
AMD
$344
AMD RX 6750 XT
12 GB VRAM • 432 GB/s
AMD
$299
Intel Arc B580
12 GB VRAM • 456 GB/s
INTEL
$249
NVIDIA Tesla K40c
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40d
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40m
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40s
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40st
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40t
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K80
12 GB VRAM • 241 GB/s
NVIDIA
NVIDIA Tesla M40
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla P100 PCIe 12 GB
12 GB VRAM • 549 GB/s
NVIDIA
NVIDIA GeForce RTX 2060 12 GB
12 GB VRAM • 336 GB/s
NVIDIA
$140
NVIDIA GeForce RTX 3060 12 GB
12 GB VRAM • 360 GB/s
NVIDIA
$329
NVIDIA GeForce RTX 3060 12 GB GA104
12 GB VRAM • 360 GB/s
NVIDIA
$329
NVIDIA GeForce RTX 3080 Ti
12 GB VRAM • 912 GB/s
NVIDIA
$1199
NVIDIA RTX A2000 12 GB
12 GB VRAM • 288 GB/s
NVIDIA
$550
AMD Radeon RX 6700 XT
12 GB VRAM • 384 GB/s
AMD
$250
Find the best GPU for DeepSeek-VL2 Small 16B
Build Hardware for DeepSeek-VL2 Small 16BModel Card
View on HuggingFaceDeepSeek VL2 Small — vision-language MoE for multimodal understanding.