SmolVLM Instruct — Hardware Requirements & GPU Compatibility
Vision
SmolVLM-Instruct is Hugging Face's 2.2-billion-parameter compact multimodal model, which accepts arbitrary sequences of images and text and returns text. It can answer questions about images, describe visual content, write stories grounded in several images, or act as a plain language model without visual input. It is built on the Idefics3 architecture, pairing a SmolLM2-1.7B language model with a SigLIP vision encoder, and compresses each 384x384 image patch into 81 visual tokens to cut memory use. At this size it runs on a single consumer GPU, even without aggressive quantization. The context length is 16,384 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in November 2024. It is the largest model in the original SmolVLM line, later followed by the smaller 500M and 256M variants that use more aggressive image compression.
33.1K downloads
600 likesSpecifications
- Publisher
- Hugging Face
- Parameters
- 2.2B
- Architecture
- Idefics3ForConditionalGeneration
- Context Length
- 16,384 tokens
- Vocabulary Size
- 49,155
- Release Date
- 2024-11-18
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does SmolVLM Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.7 GB | 4.5 GB | 0.95 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.7 GB | 4.5 GB | 0.98 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.8 GB | 4.6 GB | 1.10 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 2.0 GB | 4.9 GB | 1.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.3 GB | 5.1 GB | 1.60 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.6 GB | 5.4 GB | 1.85 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.0 GB | 5.8 GB | 2.25 GB | 8-bit quantization, near-lossless |
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 SmolVLM Instruct?
Q4_K_M · 2.0 GBSmolVLM Instruct (Q4_K_M) requires 2.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 16K context window can add up to 2.8 GB, bringing total usage to 4.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run SmolVLM Instruct?
Q4_K_M · 2.0 GB59 devices with unified memory can run SmolVLM Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download SmolVLM Instruct
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does SmolVLM Instruct need?
SmolVLM Instruct requires 2.0 GB of VRAM at Q4_K_M, or 5.2 GB at BF16. Full 16K context adds up to 2.8 GB (4.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.2B × 4.8 bits ÷ 8 = 1.3 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 3.6 GB (at full 16K context)
VRAM usage by quantization
Q4_K_M2.0 GBQ4_K_M + full context4.9 GB- What's the best quantization for SmolVLM Instruct?
For SmolVLM Instruct, Q4_K_M (2.0 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.7 GB.
VRAM requirement by quantization
Q2_K1.7 GBQ3_K_L1.9 GBQ4_K_M ★2.0 GBQ5_K_S2.3 GBQ5_K_M2.3 GBBF165.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run SmolVLM Instruct on a Mac?
SmolVLM Instruct requires at least 1.7 GB at Q2_K, 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 SmolVLM Instruct locally?
Yes — SmolVLM Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 2.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SmolVLM Instruct?
At Q4_K_M, SmolVLM Instruct can reach ~2342 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~320 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 ÷ 2.0 × 0.65 = ~2537 tok/s
Estimated speed at Q4_K_M (2.0 GB)
~2537 tok/s~320 tok/s~2537 tok/s~2342 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SmolVLM Instruct?
At Q4_K_M, the download is about 1.35 GB. The full-precision BF16 version is 4.49 GB. The smallest option (Q2_K) is 0.95 GB.
- Which GPUs can run SmolVLM Instruct?
52 consumer GPUs can run SmolVLM Instruct at Q4_K_M (2.0 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 SmolVLM Instruct?
59 devices with unified memory can run SmolVLM Instruct at Q4_K_M (2.0 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.