Small / on-device models
Sub-10B-parameter models that run on consumer GPUs or even phones. Trade-off: lower raw quality, but private, offline, and instant.
50 models in this category. See also the “Best small / on-device AI models” ranking with editorial picks and FAQ.
| Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|
| Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 262K Long context (128K+) | $0.08 | Budget | |
| Google: Gemma 4 26B A4B (free) google/gemma-4-26b-a4b-it:free | 262K Long context (128K+) | $0.00 | Budget | |
| Qwen: Qwen3 32B qwen/qwen3-32b | Qwen | 131K Long context (128K+) | $0.08 | Budget |
| LiquidAI: LFM2-8B-A1B liquid/lfm2-8b-a1b | Liquid | 33K Short/standard context | $0.01 | Budget |
| Baidu: ERNIE 4.5 VL 28B A3B baidu/ernie-4.5-vl-28b-a3b | Baidu | 30K Short/standard context | $0.14 | Budget |
| Qwen: Qwen3 8B qwen/qwen3-8b | Qwen | 131K Long context (128K+) | $0.12 | Budget |
| Mistral: Mistral 7B Instruct v0.1 mistralai/mistral-7b-instruct-v0.1 | Mistral AI | 3K Short/standard context | $0.11 | Budget |
| OpenAI: gpt-oss-120b (batch) openai/gpt-oss-120b:batch | OpenAI | 131K Long context (128K+) | $0.03 | Budget |
| OpenAI: gpt-oss-120b (exacto) openai/gpt-oss-120b:exacto | OpenAI | 131K Long context (128K+) | $0.04 | Budget |
| OpenAI: gpt-oss-120b (free) openai/gpt-oss-120b:free | OpenAI | 131K Long context (128K+) | $0.00 | Budget |
| OpenAI: gpt-oss-120b openai/gpt-oss-120b | OpenAI | 131K Long context (128K+) | $0.15 | Budget |
| Arcee AI: Trinity Mini arcee-ai/trinity-mini | Arcee Ai | 131K Long context (128K+) | $0.04 | Budget |
| Arcee AI: Trinity Mini (free) arcee-ai/trinity-mini:free | Arcee Ai | 131K Long context (128K+) | $0.00 | Budget |
| Baidu: ERNIE 4.5 21B A3B baidu/ernie-4.5-21b-a3b | Baidu | 120K Short/standard context | $0.07 | Budget |
| Cohere: North Mini Code (free) cohere/north-mini-code:free | Cohere | 256K Long context (128K+) | $0.00 | Budget |
| Google: Gemma 3n 2B (free) google/gemma-3n-e2b-it:free | 8K Short/standard context | $0.00 | Budget | |
| meta-llama/Llama-3.2-1B-Instruct meta-llama/llama-3.2-1b-instruct | Meta | 60K Short/standard context | $0.03 | Budget |
| meta-llama/Llama-3.2-3B-Instruct meta-llama/llama-3.2-3b-instruct | Meta | 131K Long context (128K+) | $0.05 | Budget |
| mudler/locate-anything.cpp-gguf huggingface/mudler/locate-anything.cpp-gguf | Hugging Face | Unknown Unknown context | Custom | Variable |
| IBM: Granite 4.0 Micro ibm-granite/granite-4.0-h-micro | Ibm Granite | 131K Long context (128K+) | $0.02 | Budget |
| inclusionAI: Ling 3.0 Flash inclusionai/ling-3.0-flash | Inclusionai | 262K Long context (128K+) | $0.02 | Budget |
| inclusionAI: Ling 3.0 Flash Fin inclusionai/ling-3.0-flash-fin | Inclusionai | 262K Long context (128K+) | $0.04 | Budget |
| inclusionAI: Ling 3.0 Flash Fin (free) inclusionai/ling-3.0-flash-fin:free | Inclusionai | 262K Long context (128K+) | $0.00 | Budget |
| inclusionAI: Ling 3.0 Flash Sante inclusionai/ling-3.0-flash-sante | Inclusionai | 262K Long context (128K+) | $0.04 | Budget |
| inclusionAI: Ling 3.0 Flash Sante (free) inclusionai/ling-3.0-flash-sante:free | Inclusionai | 262K Long context (128K+) | $0.00 | Budget |
| inclusionAI: Ling 3.0 Tiny (free) inclusionai/ling-3.0-tiny:free | Inclusionai | 262K Long context (128K+) | $0.00 | Budget |
| Ling-3.0-flash (free) inclusionai/ling-3.0-flash:free | Inclusionai | 262K Long context (128K+) | $0.00 | Budget |
| Inference.net: Schematron V2 Small inference-net/schematron-v2-small | Inference Net | 128K Long context (128K+) | $0.05 | Budget |
| Inference.net: Schematron V2 Turbo inference-net/schematron-v2-turbo | Inference Net | 128K Long context (128K+) | $0.03 | Budget |
| LiquidAI: LFM2-24B-A2B liquid/lfm-2-24b-a2b | Liquid | 33K Short/standard context | $0.03 | Budget |
| LiquidAI: LFM2.5-1.2B-Instruct (free) liquid/lfm-2.5-1.2b-instruct:free | Liquid | 33K Short/standard context | $0.00 | Budget |
| LiquidAI: LFM2.5-1.2B-Thinking (free) liquid/lfm-2.5-1.2b-thinking:free | Liquid | 33K Short/standard context | $0.00 | Budget |
| Meta: Llama 3.2 3B Instruct (free) meta-llama/llama-3.2-3b-instruct:free | Meta | 131K Long context (128K+) | $0.00 | Budget |
| NVIDIA: Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b | Nvidia | 262K Long context (128K+) | $0.06 | Budget |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) nvidia/nemotron-3-nano-30b-a3b:free | Nvidia | 256K Long context (128K+) | $0.00 | Budget |
| NVIDIA: Nemotron 3 Nano Omni (free) nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Nvidia | 256K Long context (128K+) | $0.00 | Budget |
| NVIDIA: Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning | Nvidia | 262K Long context (128K+) | $0.07 | Budget |
| NVIDIA: Nemotron 3.5 Lightning (free) nvidia/nemotron-3.5-lightning:free | Nvidia | 1M Ultra context (1M+) | $0.00 | Budget |
| NVIDIA: Nemotron Nano 12B 2 VL (free) nvidia/nemotron-nano-12b-v2-vl:free | Nvidia | 128K Long context (128K+) | $0.00 | Budget |
| Thinking Machines: Inkling Small (free) thinkingmachines/inkling-small:free | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| Upstage: Solar Mini 4 upstage/solar-mini4 | Upstage | 524K Long context (128K+) | $0.05 | Budget |
| AionLabs: Aion-1.0-Mini aion-labs/aion-1.0-mini | Aion Labs | 131K Long context (128K+) | $0.70 | Budget |
| DeepSeek: R1 Distill Qwen 32B deepseek/deepseek-r1-distill-qwen-32b | DeepSeek | 33K Short/standard context | $0.29 | Budget |
| Qwen: Qwen3 30B A3B Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 | Qwen | 262K Long context (128K+) | $0.10 | Budget |
| Meituan: LongCat Flash Chat meituan/longcat-flash-chat | Meituan | 131K Long context (128K+) | $0.20 | Budget |
| Mistral: Ministral 3 3B 2512 mistralai/ministral-3b-2512 | Mistral AI | 131K Long context (128K+) | $0.10 | Budget |
| NVIDIA: Nemotron Nano 12B 2 VL nvidia/nemotron-nano-12b-v2-vl | Nvidia | 131K Long context (128K+) | $0.20 | Budget |
| Qwen: Qwen3 Coder Next qwen/qwen3-coder-next | Qwen | 262K Long context (128K+) | $0.12 | Budget |
| Qwen: QwQ 32B qwen/qwq-32b | Qwen | 131K Long context (128K+) | $0.15 | Budget |
| Thinking Machines: Inkling Small thinkingmachines/inkling-small | Thinkingmachines | 524K Long context (128K+) | $0.45 | Budget |