GraySoft
Download guIDE →
Model Comparison

ggml-org/smolvlm2-2.2b-instruct-ggufvsunsloth/qwen3-1.7b-gguf

Side-by-side comparison of ggml-org/smolvlm2-2.2b-instruct-gguf and unsloth/qwen3-1.7b-gguf: downloads, license, context length, tasks, and benchmarks.

ggml-org/smolvlm2-2.2b-instruct-gguf

ggml-org · —

Original model: https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050

unsloth/qwen3-1.7b-gguf

unsloth · text-generation

If you are using llama.cpp, Ollama, Open WebUI etc., you can add /think and /no_think to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations. Here is an example of mu…

Side-by-side Specifications

ggml-org/smolvlm2-2.2b-instruct-ggufunsloth/qwen3-1.7b-gguf
Authorggml-orgunsloth
Pipeline Task—text-generation
Library—transformers
Downloads24,92022,966
Likes3266
LicenseUnknownUnknown
Context Length——
Created2025-04-212025-04-28
Last Modified2025-04-302025-06-08
Tags
ggufbase_model:HuggingFaceTB/SmolVLM2-2.2B-Instructbase_model:quantized:HuggingFaceTB/SmolVLM2-2.2B-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational
transformersggufqwen3text-generationqwenunslothenbase_model:Qwen/Qwen3-1.7Bbase_model:quantized:Qwen/Qwen3-1.7Blicense:apache-2.0

View full details: ggml-org/smolvlm2-2.2b-instruct-gguf · unsloth/qwen3-1.7b-gguf