Check my GPU

LLMs ·

SmolVLM2 2.2B Instruct

Parameters
2.3B
Architecture
Dense
Max context
8K tokens
License
apache-2.0
Released
2025-02

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/ggml-org/SmolVLM2-2.2B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/SmolVLM2-2.2B-Instruct-GGUF

Original weights · Hugging Face

Full-precision files from Hugging Face, for fine-tuning, vLLM, Transformers.

huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Download
Q2_K Low 0.9 GB 3.1 GB GGUF files (opens in a new tab)
Q3_K_M Low 1.1 GB 3.3 GB GGUF files (opens in a new tab)
Q4_K_M Good 1.4 GB 3.6 GB GGUF (opens in a new tab)
Q5_K_M High 1.6 GB 3.8 GB GGUF files (opens in a new tab)
Q6_K High 1.8 GB 4.1 GB GGUF files (opens in a new tab)
Q8_0 Very high 2.4 GB 4.6 GB GGUF (opens in a new tab)
F16 Full 4.5 GB 6.7 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for SmolVLM2 2.2B Instruct

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q8_0.

Grade · points Hardware Quant Memory Speed Fit
65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 NVIDIA GeForce RTX 4060 Q8_0 5.0 GB / 8.0 GB 75.5 tok/s Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.1/15 Intel Arc B580 F16 7.3 GB / 12.0 GB 44.6 tok/s Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.1/15 NVIDIA GeForce RTX 3060 12GB F16 7.3 GB / 12.0 GB 46.1 tok/s Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.1/15 NVIDIA GeForce RTX 4070 SUPER F16 7.3 GB / 12.0 GB 64.5 tok/s Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 AMD Radeon RX 9070 XT F16 7.5 GB / 16.0 GB 70.5 tok/s Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 7.5 GB / 16.0 GB 86.0 tok/s Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 4080 SUPER F16 7.5 GB / 16.0 GB 94.2 tok/s Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 5060 Ti 16GB F16 7.5 GB / 16.0 GB 57.3 tok/s Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 5070 Ti F16 7.5 GB / 16.0 GB 115 tok/s Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 5080 F16 7.5 GB / 16.0 GB 123 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.