All LLM Models
Browse 593 LLM models with VRAM requirements, quantization options, and hardware compatibility.
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.
Model List
Phi 4 Quantized.w8a8
RedHatAI · 14.7B · runs from 7.0 GB
438
3Phi 4 Quantized.w8a8 is a 14.7B-parameter open language model from RedHatAI in the Phi 4 family. It supports a context window of up to 16,384 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
LFM2 350M Extract
LiquidAI · 354M · runs from 0.5 GB
LFM2 350M Extract is a 354M-parameter open language model from LiquidAI. 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.
Dolphin X1 Trinity Nano
dphn · 6.1B · runs from 3.0 GB
Dolphin X1 Trinity Nano is a 6.1B-parameter open language model from dphn in the Phi 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.
Apertus 8B MeditronFO
EPFLiGHT · 8.1B · runs from 4.0 GB
Apertus 8B MeditronFO is a 8.1B-parameter open language model from EPFLiGHT in the Apertus family. It supports a context window of up to 65,536 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
CyberPal2.0 20B
cyber-pal-security · 20.9B · runs from 9.3 GB
CyberPal2.0 20B is a 20.9B-parameter open language model from cyber-pal-security. 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.
Jan V3.5 4B
janhq · 4.4B · runs from 2.4 GB
Jan V3.5 4B is a 4.4B-parameter open language model from janhq. 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.
Kimi K2.6 Eagle3
NVIDIA · 1.8B · runs from 1.1 GB
Kimi K2.6 Eagle3 is a 1.8B-parameter open language model from NVIDIA in the Kimi K2 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.
II Medical 8B 1706
Intelligent-Internet · 8.2B · runs from 4.1 GB
II Medical 8B 1706 is a 8.2B-parameter open language model from Intelligent-Internet. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Quark 135M
ThingAI · 135M · runs from 0.4 GB
Quark 135M is a 135M-parameter open language model from ThingAI. 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.
Qwen2.5 Omni 3B MNN
taobao-mnn · 3B · runs from 6.6 GB
Qwen2.5 Omni 3B MNN is a 3B-parameter open language model from taobao-mnn in the Qwen 2.5 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
DeepSeek R1 Distill Qwen 14B Abliterated v2
huihui-ai · 14.8B · runs from 7.0 GB
DeepSeek R1 Distill Qwen 14B Abliterated v2 is a 14.8B-parameter open language model from huihui-ai in the DeepSeek R1 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.
Luciole 1B Base
OpenLLM-France · 1.3B · runs from 1.0 GB
Luciole 1B Base is a 1.3B-parameter open language model from OpenLLM-France. 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.
Dhara 70M
codelion · 71M · runs from 0.5 GB
Dhara 70M is a 71M-parameter open language model from codelion. 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.
Gemma3 1B CulturaViva ITA
nickprock · 1000M · runs from 0.8 GB
Gemma3 1B CulturaViva ITA is a 1000M-parameter open language model from nickprock in the Gemma 3 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.
Supra Mini V5 8M
SupraLabs · 8M · runs from 0.3 GB
Supra Mini V5 8M is a 8M-parameter open language model from SupraLabs. 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.
Qwen3 14B PARO
z-lab · 1.6B · runs from 1.3 GB
Qwen3 14B PARO is a 1.6B-parameter open language model from z-lab in the Qwen 3 family. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Claim Extractor 2B Q 2605
principled-intelligence · 2.3B · runs from 5.0 GB
Claim Extractor 2B Q 2605 is a 2.3B-parameter open language model from principled-intelligence. 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.
Nemotron Terminal 14B
NVIDIA · 14.8B · runs from 6.9 GB
Nemotron Terminal 14B is a 14.8B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Aryabhata 2.0
PhysicsWallahAI · 20.9B · runs from 9.3 GB
Aryabhata 2.0 is a 20.9B-parameter open language model from PhysicsWallahAI. 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.
T5gemma B B Ul2 IT
Google · 591M · runs from 1.3 GB
T5gemma B B Ul2 IT is a 591M-parameter open language model from Google in the Gemma family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Archaea 74M
GODELEV · 74M · runs from 0.3 GB
Archaea 74M is a 74M-parameter open language model from GODELEV. 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.
Nerdsking Python Coder 7B I
Nerdsking · 7B · runs from 3.3 GB
Nerdsking Python Coder 7B I is a 7B-parameter open language model from Nerdsking. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Datarus R1 14B Preview
DatarusAI · 14.8B · runs from 7.0 GB
Datarus R1 14B Preview is a 14.8B-parameter open language model from DatarusAI. 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.
Qwen3 Code Reasoning 4B
GetSoloTech · 4B · runs from 2.2 GB
Qwen3 Code Reasoning 4B is a 4B-parameter open language model from GetSoloTech 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.
JOSIE 1.1 4B Instruct
Goekdeniz-Guelmez · 4.0B · runs from 2.2 GB
JOSIE 1.1 4B Instruct is a 4.0B-parameter open language model from Goekdeniz-Guelmez. 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.
MN VelvetCafe RP 12B
IggyLux · 12.2B · runs from 5.9 GB
MN VelvetCafe RP 12B is a 12.2B-parameter open language model from IggyLux. 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.
SmolLM3 3B ONNX
Hugging Face · 3B · runs from 1.7 GB
SmolLM3 3B ONNX is a 3B-parameter open language model from Hugging Face in the SmolLM family. It supports a context window of up to 65,536 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Gemma 3 270M IT Heretic
p-e-w · 268M · runs from 0.4 GB
Gemma 3 270M IT Heretic is a 268M-parameter open language model from p-e-w in the Gemma 3 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.
Scout 4B
vanta-research · 4.3B · runs from 2.5 GB
Scout 4B is a 4.3B-parameter open language model from vanta-research. 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.
Protocol Phantom 12B
DarkArtsForge · 12.2B · runs from 5.9 GB
Protocol Phantom 12B is a 12.2B-parameter open language model from DarkArtsForge. 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.