Penguin VL 8B — Hardware Requirements & GPU Compatibility
ChatVision
Penguin VL 8B is a 8.7B-parameter open language model from Tencent. It supports a context window of up to 40,960 tokens. At BF16 it needs about 17.91 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs on 24 GB (BF16 · ~37 tok/s · 40K)Macs from 24 GB (BF16 · ~12 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Penguin VL 8B
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-8B --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 3090 (24 GB) (4 GB headroom) · BF16
- Generation speed
- ~34 tok/s
- generation speed
- Cost per 1M output tokens
- $1.49
- per 1M output tokens
How Much VRAM Does Penguin VL 8B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 17.9 GB | 22.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 40K context · ~37 tok/s |
Selected BF16
Brain floating point 1620.0GBat 16K context
- Weights
- 17.3 GB
- KV cache
- 2.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.0 GB free · ~37 tok/s
≥50 tok/s needs ≥1.38 TB/s · RTX 5090 ~65
Which Hardware Can Run Penguin VL 8B?
BF16 · 17.9 GBPenguin VL 8B (BF16) requires 17.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. Using the full 41K context window can add up to 5.7 GB, bringing total usage to 23.6 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Penguin VL 8B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
tight · up to 8K ctx
1 GPU
RX 7900 XT~27Simulate output on RX 7900 XT32–40 GB
fits · 12.0 GB free · up to 40K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~65Simulate output on RTX 5090M5 Max36 GB~18Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate 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 |
|---|---|---|---|---|
| Granite Switch 4.1 8BIBM | — | 8.4 GB | ~111 | same size |
| Apertus V1.5 8Bswiss-ai | — | 8.5 GB | ~111 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| Qwen3 VL 8B InstructAlibaba | — | 8 GB | ~112 | same size |
| MiniCPM V 4 5OpenBMB | — | 7.9 GB | ~113 | same size |
| Llama 3.1 Nemotron Nano VL 8B V1NVIDIA | — | 8.4 GB | ~114 | same size |
Specifications
- Publisher
- Tencent
- Parameters
- 8.7B
- 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 8B need?
Penguin VL 8B requires 17.9 GB of VRAM at BF16. Full 41K context adds up to 5.7 GB (23.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.7B × 16 bits ÷ 8 = 17.3 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 ≈ 6.3 GB (at full 41K context)
VRAM usage by quantization
Can I run Penguin VL 8B on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Penguin VL 8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 17.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Penguin VL 8B locally?
Yes — Penguin VL 8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Penguin VL 8B?
At BF16, Penguin VL 8B can reach ~268 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~37 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 ÷ 17.91 × 0.65 = ~290 tok/s
Estimated speed at BF16 (17.9 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 8B?
At BF16, the download is about 17.31 GB.
Which GPUs can run Penguin VL 8B?
8 consumer GPUs can run Penguin VL 8B at BF16. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Penguin VL 8B?
122 devices with unified memory can run Penguin VL 8B at BF16 (17.9 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.