Skip to content

SmolLM2 1.7B

by Hugging Face · smollm family

1.7B

parameters

text-generation code-generation summarization

SmolLM2 1.7B is Hugging Face's compact language model designed for on-device and edge deployment. Trained on 11 trillion tokens from a diverse mix of web data, code, and mathematics datasets, it delivers surprisingly strong performance for its size. Despite being one of the smallest models available, SmolLM2 1.7B outperforms other models in its class on reasoning, knowledge, and instruction-following tasks. Its tiny VRAM footprint makes it ideal for resource-constrained environments where larger models are impractical.

Quick Start with Ollama

ollama run 1.7b-instruct-q8_0
Resources Ollama Hugging Face Official Page
Creator Hugging Face
Parameters 1.7B
Architecture transformer-decoder
Context 8K tokens
Released Nov 2, 2024
License Apache 2.0
Ollama smollm2

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M 1 GB 1.9 GB 1.7b-instruct-q4_K_M
Q8_0 rec 1.8 GB 2.7 GB 1.7b-instruct-q8_0
F16 3.4 GB 4.4 GB 1.7b-instruct-fp16

Compatible Hardware

Q8_0 requires 2.7 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~303 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~296 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~303 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~202 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~202 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~202 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~711 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~148 tok/s
Mac mini M4 Pro 64GB64 GBmacRuns~101 tok/s
Mac Studio M4 Max 64GB64 GBmacRuns~202 tok/s
MacBook Pro M4 Max 64GB64 GBmacRuns~202 tok/s
MacBook Pro M5 Max 64GB64 GBmacRuns~202 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuRuns~356 tok/s
NVIDIA RTX A600048 GBgpuRuns~284 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuRuns~356 tok/s
Mac mini M4 Pro 48GB48 GBmacRuns~101 tok/s
MacBook Pro M3 Max 48GB48 GBmacRuns~148 tok/s
MacBook Pro M4 Max 48GB48 GBmacRuns~202 tok/s
MacBook Pro M4 Pro 48GB48 GBmacRuns~101 tok/s
MacBook Pro M5 Max 48GB48 GBmacRuns~152 tok/s
MacBook Pro M5 Pro 48GB48 GBmacRuns~101 tok/s
Mac Studio M4 Max 36GB36 GBmacRuns~202 tok/s
MacBook Pro M3 Pro 36GB36 GBmacRuns~56 tok/s
MacBook Pro M5 Max 36GB36 GBmacRuns~152 tok/s
NVIDIA RTX 5000 Ada Generation32 GBgpuRuns~267 tok/s
NVIDIA GeForce RTX 509032 GBgpuRuns~664 tok/s
iMac M4 32GB32 GBmacRuns~44 tok/s
Mac mini M4 32GB32 GBmacRuns~44 tok/s
MacBook Air M5 32GB32 GBmacRuns~44 tok/s
MacBook Air M4 32GB32 GBmacRuns~44 tok/s
MacBook Pro M5 32GB32 GBmacRuns~44 tok/s
AMD Radeon RX 7900 XTX24 GBgpuRuns~356 tok/s
NVIDIA GeForce RTX 3090 Ti24 GBgpuRuns~373 tok/s
NVIDIA GeForce RTX 309024 GBgpuRuns~347 tok/s
NVIDIA GeForce RTX 409024 GBgpuRuns~373 tok/s
NVIDIA RTX A500024 GBgpuRuns~284 tok/s
iMac M3 24GB24 GBmacRuns~37 tok/s
Mac mini M2 24GB24 GBmacRuns~37 tok/s
Mac mini M4 Pro 24GB24 GBmacRuns~101 tok/s
MacBook Air M2 24GB24 GBmacRuns~37 tok/s
MacBook Air M4 24GB24 GBmacRuns~44 tok/s
MacBook Air M5 24GB24 GBmacRuns~44 tok/s
MacBook Pro M4 Pro 24GB24 GBmacRuns~101 tok/s
MacBook Pro M5 24GB24 GBmacRuns~44 tok/s
MacBook Pro M5 Pro 24GB24 GBmacRuns~101 tok/s
AMD Radeon RX 7900 XT20 GBgpuRuns~296 tok/s
NVIDIA RTX 4000 Ada Generation20 GBgpuRuns~133 tok/s
MacBook Pro M3 Pro 18GB18 GBmacRuns~56 tok/s
AMD Radeon RX 6800 XT16 GBgpuRuns~190 tok/s
AMD Radeon RX 6900 XT16 GBgpuRuns~190 tok/s
AMD Radeon RX 7800 XT16 GBgpuRuns~231 tok/s
AMD Radeon RX 9060 XT 16GB16 GBgpuRuns~199 tok/s
AMD Radeon RX 9070 XT16 GBgpuRuns~241 tok/s
AMD Radeon RX 907016 GBgpuRuns~199 tok/s
Intel Arc A77016 GBgpuRuns~207 tok/s
NVIDIA GeForce RTX 4060 Ti 16GB16 GBgpuRuns~107 tok/s
NVIDIA GeForce RTX 4070 Ti Super16 GBgpuRuns~249 tok/s
NVIDIA GeForce RTX 4080 Super16 GBgpuRuns~273 tok/s
NVIDIA GeForce RTX 408016 GBgpuRuns~266 tok/s
NVIDIA GeForce RTX 5060 Ti 16GB16 GBgpuRuns~166 tok/s
NVIDIA GeForce RTX 5070 Ti16 GBgpuRuns~332 tok/s
NVIDIA GeForce RTX 508016 GBgpuRuns~356 tok/s
NVIDIA RTX A400016 GBgpuRuns~166 tok/s
iMac M1 16GB16 GBmacRuns~25 tok/s
iMac M4 16GB16 GBmacRuns~44 tok/s
Mac mini M1 16GB16 GBmacRuns~25 tok/s
Mac mini M4 16GB16 GBmacRuns~44 tok/s
MacBook Air M2 16GB16 GBmacRuns~37 tok/s
MacBook Air M4 16GB16 GBmacRuns~44 tok/s
MacBook Air M3 16GB16 GBmacRuns~37 tok/s
MacBook Air M5 16GB16 GBmacRuns~44 tok/s
MacBook Pro M2 Pro 16GB16 GBmacRuns~74 tok/s
MacBook Pro M1 16GB16 GBmacRuns~25 tok/s
MacBook Pro M5 16GB16 GBmacRuns~44 tok/s
AMD Radeon RX 6700 XT12 GBgpuRuns~142 tok/s
AMD Radeon RX 7700 XT12 GBgpuRuns~160 tok/s
Intel Arc B58012 GBgpuRuns~169 tok/s
NVIDIA GeForce RTX 3060 12GB12 GBgpuRuns~133 tok/s
NVIDIA GeForce RTX 3080 12GB12 GBgpuRuns~338 tok/s
NVIDIA GeForce RTX 4070 Super12 GBgpuRuns~187 tok/s
NVIDIA GeForce RTX 4070 Ti12 GBgpuRuns~187 tok/s
NVIDIA GeForce RTX 407012 GBgpuRuns~187 tok/s
NVIDIA GeForce RTX 507012 GBgpuRuns~249 tok/s
NVIDIA GeForce GTX 1080 Ti11 GBgpuRuns~179 tok/s
NVIDIA GeForce RTX 2080 Ti11 GBgpuRuns~228 tok/s
Intel Arc B57010 GBgpuRuns~141 tok/s
NVIDIA GeForce RTX 3080 10GB10 GBgpuRuns~281 tok/s
AMD Radeon RX 6600 XT8 GBgpuRuns~95 tok/s
AMD Radeon RX 76008 GBgpuRuns~107 tok/s
AMD Radeon RX 9060 XT 8GB8 GBgpuRuns~100 tok/s
Intel Arc A7508 GBgpuRuns~190 tok/s
NVIDIA GeForce GTX 10708 GBgpuRuns~95 tok/s
NVIDIA GeForce RTX 2060 Super8 GBgpuRuns~166 tok/s
NVIDIA GeForce RTX 2070 Super8 GBgpuRuns~166 tok/s
NVIDIA GeForce RTX 2080 Super8 GBgpuRuns~184 tok/s
NVIDIA GeForce RTX 30508 GBgpuRuns~83 tok/s
NVIDIA GeForce RTX 3060 Ti8 GBgpuRuns~166 tok/s
NVIDIA GeForce RTX 30708 GBgpuRuns~166 tok/s
NVIDIA GeForce RTX 4060 Ti 8GB8 GBgpuRuns~107 tok/s
NVIDIA GeForce RTX 40608 GBgpuRuns~101 tok/s
NVIDIA GeForce RTX 50508 GBgpuRuns~83 tok/s
NVIDIA GeForce RTX 5060 Ti 8GB8 GBgpuRuns~166 tok/s
NVIDIA GeForce RTX 50608 GBgpuRuns~124 tok/s
MacBook Air M1 8GB8 GBmacRuns~25 tok/s
MacBook Air M2 8GB8 GBmacRuns~37 tok/s
NVIDIA GeForce GTX 1660 Super6 GBgpuRuns~124 tok/s
NVIDIA GeForce RTX 20606 GBgpuRuns~124 tok/s