Penguin VL 2B — Hardware Requirements & GPU Compatibility
ChatVision
Penguin VL 2B is a 2.2B-parameter open language model from Tencent. It supports a context window of up to 40,960 tokens. At BF16 it needs about 4.87 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 16K)Best on 24 GB (BF16 · ~135 tok/s · 40K)Macs from 16 GB (BF16 · ~29 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Penguin VL 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
vllm serve tencent/Penguin-VL-2B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (5 GB headroom) · BF16
- Generation speed
- ~122 tok/s
- generation speed
- Cost per 1M output tokens
- $0.28
- per 1M output tokens
How Much VRAM Does Penguin VL 2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.9 GB | 8.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 40K context · ~135 tok/s |
Selected BF16
Brain floating point 166.5GBat 16K context
- Weights
- 4.3 GB
- KV cache
- 1.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 17.5 GB free · ~135 tok/s
≥50 tok/s needs ≥374 GB/s · RTX 5090 ~239, RTX 3090 Ti ~135
Which Hardware Can Run Penguin VL 2B?
BF16 · 4.9 GBPenguin VL 2B (BF16) requires 4.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 41K context window can add up to 4.5 GB, bringing total usage to 9.3 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Penguin VL 2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 1.5 GB free · up to 16K ctx
16 GPUs · 2 device families
RTX 3080~102Simulate output on RTX 3080RTX 2080 Ti~82Simulate output on RTX 2080 TiRTX 3070 Ti~81Simulate output on RTX 3070 TiOrin Nano~14Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~10Simulate output on iPhone 1720 GB
fits · 13.5 GB free · up to 40K ctx
1 GPU
RX 7900 XT~99Simulate output on RX 7900 XT32–40 GB
fits · 25.5 GB free · up to 40K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~239Simulate output on RTX 5090M5 Max36 GB~66Simulate output on Mac Studio M5 Max (36 GB)M532 GB~22Simulate output on MacBook Air 13" M5 (32 GB)Orin~27Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~18Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM3 Omni 2BLiquid AI | — | 2.4 GB | ~385 | same size |
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| Qwen3 VL 2B InstructAlibaba | — | 3.5 GB | ~362 | same size |
| Qwen2 VL 2B InstructAlibaba | — | 2.1 GB | ~390 | same size |
| Kimi K3 DSparkRadixArk | — | 2.2 GB | ~381 | same size |
| Qwen3.8 2Bempero-ai | — | 1.9 GB | ~370 | same size |
Specifications
- Publisher
- Tencent
- Parameters
- 2.2B
- Architecture
- PenguinVLQwen3ForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-03-05
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Penguin VL 2B need?
Penguin VL 2B requires 4.9 GB of VRAM at BF16. Full 41K context adds up to 4.5 GB (9.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.2B × 16 bits ÷ 8 = 4.3 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 5 GB (at full 41K context)
VRAM usage by quantization
Can I run Penguin VL 2B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Penguin VL 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 4.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Penguin VL 2B locally?
Yes — Penguin VL 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Penguin VL 2B?
At BF16, Penguin VL 2B can reach ~986 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~135 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 ÷ 4.87 × 0.65 = ~1068 tok/s
Estimated speed at BF16 (4.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Penguin VL 2B?
At BF16, the download is about 4.34 GB.
Which GPUs can run Penguin VL 2B?
52 consumer GPUs can run Penguin VL 2B at BF16. 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 Penguin VL 2B?
151 devices with unified memory can run Penguin VL 2B at BF16 (4.9 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.