All LLM Models

Browse 982 LLM models with VRAM requirements, quantization options, and hardware compatibility.

Featured only

Understanding LLM VRAM Requirements

How much VRAM you need depends on the model size and quantization level. Quantization reduces the precision of model weights, trading small quality losses for significantly lower VRAM usage. For example, a 7B parameter model needs ~14 GB at FP16 but only ~4 GB at Q4_K_M quantization.

PowerLM 3B

ibm-research · 3.5B · runs from 2.5 GB

PowerLM 3B is a 3.5B-parameter open language model from ibm-research. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Opt 2.7B

Meta · 2.7B · runs from 5.9 GB

Opt 2.7B is a 2.7B-parameter open language model from Meta. It supports a context window of up to 2,048 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Stablelm 3B 4e1t

Stability AI · 2.8B · runs from 2.2 GB

Stablelm 3B 4e1t is a 2.8B-parameter open language model from Stability AI in the StableLM family. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Tiny LLM

arnir0 · 13M · runs from 0.3 GB

Tiny LLM is a 13M-parameter open language model from arnir0. It supports a context window of up to 1,024 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Llama 3 8B Instruct Gradient 1048k

gradientai · 8.0B · runs from 4.0 GB

Llama 3 8B Instruct Gradient 1048k is a 8.0B-parameter open language model from gradientai in the Llama 3 family. It supports a context window of up to 1,048,576 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Granite 3.1 8B Instruct

IBM · 8.2B · runs from 4.1 GB

Granite 3.1 8B Instruct is a 8.2B-parameter open language model from IBM in the Granite family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Beetle Monolingual Humanscale Eng

Beetle-HumanScale · 194M · runs from 0.4 GB

Beetle Monolingual Humanscale Eng is a 194M-parameter open language model from Beetle-HumanScale. It supports a context window of up to 512 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Typhoon2.5 Qwen3 4B

typhoon-ai · 4.0B · runs from 2.2 GB

Typhoon2.5 Qwen3 4B is a 4.0B-parameter open language model from typhoon-ai in the Qwen 3 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

GPT OSS Safeguard 20B

OpenAI · 21.5B · runs from 9.5 GB

GPT OSS Safeguard 20B is a 21.5B-parameter open language model from OpenAI in the GPT-OSS family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Granite 3.0 8B Instruct

IBM · 8.2B · runs from 4.1 GB

Granite 3.0 8B Instruct is a 8.2B-parameter open language model from IBM in the Granite family. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

SedibaLM

Sedibaai · 1.5B · runs from 1.0 GB

SedibaLM is a 1.5B-parameter open language model from Sedibaai. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Hermes 2 Pro Mistral 7B

Nous Research · 7.2B · runs from 3.6 GB

Hermes 2 Pro Mistral 7B is a 7.2B-parameter open language model from Nous Research in the Mistral family. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Qwen1.5 0.5B

Alibaba · 620M · runs from 0.8 GB

Qwen1.5 0.5B is a 620M-parameter open language model from Alibaba in the Qwen family. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Qwen 7B Chat

Alibaba · 7.7B · runs from 3.6 GB

Qwen 7B Chat is a 7.7B-parameter open language model from Alibaba in the Qwen family. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Granite 3B Code Base 2k

IBM · 3.5B · runs from 2.5 GB

Granite 3B Code Base 2k is a 3.5B-parameter open language model from IBM in the Granite family. It supports a context window of up to 2,048 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Gemma 2 9B

Google · 9.2B · runs from 4.3 GB

Gemma 2 9B is a 9.2B-parameter open language model from Google in the Gemma 2 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Nandi Mini 150M

FrontiersMind · 153M · runs from 0.6 GB

Nandi Mini 150M is a 153M-parameter open language model from FrontiersMind. It supports a context window of up to 2,048 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Granite 4.0 1B Base

IBM · 1.6B · runs from 1.2 GB

Granite 4.0 1B Base is a 1.6B-parameter open language model from IBM in the Granite family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Openthaigpt1.5 7B Instruct

openthaigpt · 7.6B · runs from 3.6 GB

Openthaigpt1.5 7B Instruct is a 7.6B-parameter open language model from openthaigpt. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Academic Ds 9B

ByteDance-Seed · 9.4B · runs from 4.5 GB

Academic Ds 9B is a 9.4B-parameter open language model from ByteDance-Seed. It supports a context window of up to 8,192 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Qwen2.5 Coder 0.5B

Alibaba · 494M · runs from 0.5 GB

Qwen2.5 Coder 0.5B is a 494-million parameter code-specialized model from Alibaba Cloud, the smallest in the Qwen 2.5 Coder series. It is designed for ultra-lightweight deployment where code-aware text generation is needed with minimal hardware resources. The model runs on virtually any GPU and even on CPU-only setups. While limited in capability compared to larger coding models, it is useful for basic code completion, prototyping, and experimentation. It supports a 128K token context window. Released under the Apache 2.0 license.

Llama XLAM 2 8B Fc R

Salesforce · 8.0B · runs from 4.0 GB

xLAM 2 8B FC-R is an 8-billion parameter model by Salesforce, specifically optimized for function calling and tool use. Built on the Llama architecture, it is designed to reliably generate structured function call outputs, making it suitable for agentic workflows and applications that require models to interact with external tools and APIs. Unlike general-purpose chat models, xLAM 2 focuses on accurately parsing user intent into structured tool invocations with proper argument formatting. It runs on consumer GPUs with 8GB or more of VRAM and is a strong choice for developers building local AI agent systems that need reliable function-calling capabilities.

Pythia 2.8B

EleutherAI · 2.9B · runs from 1.4 GB

Pythia 2.8B is a 2.9B-parameter open language model from EleutherAI. It supports a context window of up to 2,048 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

LFM2.5 350M Base

Liquid AI · 354M · runs from 0.5 GB

LFM2.5 350M Base is a 354M-parameter open language model from Liquid AI in the LFM2.5 family. It supports a context window of up to 128,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Llava Onevision Qwen2 7B Ov

lmms-lab · 8.0B · runs from 3.8 GB

Llava Onevision Qwen2 7B Ov is a 8.0B-parameter open language model from lmms-lab in the Qwen 2 family. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

H2ovl Mississippi 800M

h2oai · 826M · runs from 1.8 GB

H2ovl Mississippi 800M is a 826M-parameter open language model from h2oai. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Smollm2 360M Aac Watch

dcostenco · 360M · runs from 0.2 GB

Smollm2 360M Aac Watch is a 360M-parameter open language model from dcostenco in the SmolLM family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

SOLAR 10.7B Instruct v1.0

Upstage · 10.7B · runs from 5.3 GB

SOLAR 10.7B Instruct v1.0 is a 10.7B-parameter open language model from Upstage in the Solar family. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Deepseek Coder 1.3B Instruct

DeepSeek · 1.3B · runs from 1.3 GB

DeepSeek Coder 1.3B Instruct is an ultra-compact code model designed for environments where hardware resources are extremely limited. Despite having just 1.3 billion parameters, it can handle basic code completion, simple generation tasks, and code Q&A across common programming languages. This is one of the smallest viable code models available, capable of running on integrated graphics or very low-end dedicated GPUs. It is well suited for edge deployment, embedded development environments, or as a fast local autocomplete engine where response speed matters more than handling complex multi-file reasoning tasks.

Deepseek Llm 7B Base

DeepSeek · 7B · runs from 4.3 GB

Deepseek Llm 7B Base is a 7B-parameter open language model from DeepSeek in the DeepSeek family. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.