SmolVLM2 256M Video Instruct — Hardware Requirements & GPU Compatibility
Vision
SmolVLM2-256M-Video-Instruct is Hugging Face's 256-million-parameter multimodal model for analyzing video, images and text, producing text answers. It handles video question answering, captioning, comparing visual content and transcribing text from images, and does not generate images or video. It is fine-tuned from SmolVLM-256M-Instruct, and the card says video inference needs only about 1.38 GB of GPU RAM. The card lists Video-MME 33.7, MLVU 40.6 and MVBench 32.7, the lowest of the three SmolVLM2 sizes. It runs on almost any hardware, including laptops, phone-class devices and CPUs. The context length is 8,192 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in February 2025. It is the smallest of the SmolVLM2 family, which also includes 500M and 2.2B versions, and the card lists English as its language.
43.0K downloads
115 likesSpecifications
- Publisher
- Hugging Face
- Parameters
- 256M
- Architecture
- SmolVLMForConditionalGeneration
- Context Length
- 8,192 tokens
- Vocabulary Size
- 49,280
- Release Date
- 2025-02-11
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does SmolVLM2 256M Video Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 0.5 GB | 0.6 GB | 0.11 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 0.5 GB | 0.6 GB | 0.11 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 0.5 GB | 0.6 GB | 0.13 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 0.5 GB | 0.6 GB | 0.13 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 0.5 GB | 0.6 GB | 0.15 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 0.5 GB | 0.7 GB | 0.18 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 0.6 GB | 0.7 GB | 0.21 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 0.6 GB | 0.8 GB | 0.26 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run SmolVLM2 256M Video Instruct?
Q4_K_M · 0.5 GBSmolVLM2 256M Video Instruct (Q4_K_M) requires 0.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 8K context window can add up to 0.1 GB, bringing total usage to 0.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run SmolVLM2 256M Video Instruct?
Q4_K_M · 0.5 GB59 devices with unified memory can run SmolVLM2 256M Video Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download SmolVLM2 256M Video Instruct
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does SmolVLM2 256M Video Instruct need?
SmolVLM2 256M Video Instruct requires 0.5 GB of VRAM at Q4_K_M, or 0.9 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 256M × 4.8 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.4 GB (at full 8K context)
VRAM usage by quantization
Q4_K_M0.5 GBQ4_K_M + full context0.6 GB- What's the best quantization for SmolVLM2 256M Video Instruct?
For SmolVLM2 256M Video Instruct, Q4_K_M (0.5 GB) offers the best balance of quality and VRAM usage. Q5_0 (0.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XS at 0.4 GB.
VRAM requirement by quantization
IQ2_XS0.4 GBQ2_K_S0.5 GBQ4_00.5 GBQ4_K_M ★0.5 GBQ5_00.5 GBBF160.9 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run SmolVLM2 256M Video Instruct on a Mac?
SmolVLM2 256M Video Instruct requires at least 0.4 GB at IQ2_XS, 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 SmolVLM2 256M Video Instruct locally?
Yes — SmolVLM2 256M Video Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 0.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SmolVLM2 256M Video Instruct?
At Q4_K_M, SmolVLM2 256M Video Instruct can reach ~9600 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1310 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 ÷ 0.5 × 0.65 = ~10400 tok/s
Estimated speed at Q4_K_M (0.5 GB)
~10400 tok/s~1310 tok/s~10400 tok/s~9600 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SmolVLM2 256M Video Instruct?
At Q4_K_M, the download is about 0.15 GB. The full-precision BF16 version is 0.51 GB. The smallest option (IQ2_XS) is 0.08 GB.
- Which GPUs can run SmolVLM2 256M Video Instruct?
52 consumer GPUs can run SmolVLM2 256M Video Instruct at Q4_K_M (0.5 GB). 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 SmolVLM2 256M Video Instruct?
59 devices with unified memory can run SmolVLM2 256M Video Instruct at Q4_K_M (0.5 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.