All LLM Models
Browse 1475 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
Supra 50M Instruct
SupraLabs · 52M · runs from 0.3 GB
9.1K
55Supra 50M Instruct is a 52M-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.
Meta Llama 3 8B Instruct Abliterated v3
failspy · 8.0B · runs from 4.0 GB
Meta Llama 3 8B Instruct Abliterated v3 is a 8.0B-parameter open language model from failspy in the Llama 3 family. 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.
Qwen3.8 27B AEON ULTIMATE UNCENSORED BF16
AEON-7 · 27.8B · runs from 56.3 GB
Qwen3.8 27B AEON ULTIMATE UNCENSORED BF16 is a 27.8B-parameter open language model from AEON-7 in the Qwen 3.8 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.
Dolphin 2.9.1 Llama 3 70B
dphn · 70.6B · runs from 31.0 GB
Dolphin 2.9.1 Llama 3 70B is a 70.6B-parameter open language model from dphn in the Llama 3 family. 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.
VibeThinker 3B
WeiboAI · 3.1B · runs from 1.7 GB
VibeThinker 3B is a 3.1B-parameter open language model from WeiboAI. 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.
DeepSeek R1 Zero
DeepSeek · 684.5B · runs from 294.8 GB
DeepSeek R1 Zero is a 684.5B-parameter open language model from DeepSeek in the DeepSeek R1 family. It supports a context window of up to 163,840 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Ouro 2.6B
ByteDance · 2.7B · runs from 6.4 GB
Ouro 2.6B is a 2.7B-parameter open language model from ByteDance. 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.
Title
desert-ant-labs · 352M · runs from 0.5 GB
Title is a 352M-parameter open language model from desert-ant-labs. 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.
ALLaM 7B Instruct Preview
humain-ai · 7.0B · runs from 4.3 GB
ALLaM 7B Instruct Preview is a 7.0B-parameter open language model from humain-ai. 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.
Qwen3.8 27B ABLITERATED BF16
Blackfrost-AI · 27.8B · runs from 56.3 GB
Qwen3.8 27B ABLITERATED BF16 is a 27.8B-parameter open language model from Blackfrost-AI in the Qwen 3.8 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.
IQuest Coder V1 40B Loop Instruct
IQuestLab · 39.8B · runs from 80.6 GB
IQuest Coder V1 40B Loop Instruct is a 39.8B-parameter open language model from IQuestLab. 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.
Huihui Qwen3 8B Abliterated v2
huihui-ai · 8.2B · runs from 4.1 GB
Huihui Qwen3 8B Abliterated v2 is a 8.2B-parameter open language model from huihui-ai 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.
Qwen Marketing
marketeam · 8.2B · runs from 18.0 GB
Qwen Marketing is a 8.2B-parameter open language model from marketeam in the Qwen family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Midnight Miqu 70B V1.5
sophosympatheia · 69.0B · runs from 30.3 GB
Midnight Miqu 70B V1.5 is a 69.0B-parameter open language model from sophosympatheia. It supports a context window of up to 32,764 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Ternary Bonsai 2 27B MTP
ProCreations · 27B · runs from 12.6 GB
Ternary Bonsai 2 27B MTP is a 27B-parameter open language model from ProCreations. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.8 27B MTPLX Optimized Speed FP16
Youssofal · 27.4B · runs from 55.5 GB
Qwen3.8 27B MTPLX Optimized Speed FP16 is a 27.4B-parameter open language model from Youssofal in the Qwen 3.8 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.
Granite Switch 4.1 3B Preview
IBM · 4.1B · runs from 8.8 GB
Granite Switch 4.1 3B Preview is a 4.1B-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.
Goedel Prover v2 8B
Goedel-LM · 8.2B · runs from 4.1 GB
Goedel Prover v2 8B is a 8.2B-parameter open language model from Goedel-LM. 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.
Meta Llama Guard 2 8B
Meta · 8.0B · runs from 17.7 GB
Meta Llama Guard 2 8B is a 8.0B-parameter open language model from Meta in the Llama family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Mamba 1.4B HF
State Spaces · 1.4B · runs from 0.6 GB
Mamba 1.4B HF is a 1.4B-parameter open language model from State Spaces. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama3 8B Chinese Chat
shenzhi-wang · 8.0B · runs from 4.0 GB
Llama3 8B Chinese Chat is a 8.0B-parameter open language model from shenzhi-wang in the Llama 3 family. 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.
MiniCPM5 1B Base
OpenBMB · 1.1B · runs from 0.8 GB
MiniCPM5 1B Base is a 1.1B-parameter open language model from OpenBMB in the MiniCPM 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.
Mamba 2.8B HF
State Spaces · 2.8B · runs from 1.3 GB
Mamba 2.8B HF is a 2.8B-parameter open language model from State Spaces. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Mixtral 34Bx2 MoE 60B
cloudyu · 60.8B · runs from 26.6 GB
Mixtral 34Bx2 MoE 60B is a 60.8B-parameter open language model from cloudyu in the Mixtral family. It supports a context window of up to 200,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
MiniCPM5 2B Base
OpenBMB · 2.5B · runs from 1.5 GB
MiniCPM5 2B Base is a 2.5B-parameter open language model from OpenBMB in the MiniCPM family. It supports a context window of up to 524,288 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Gemma 2 2B Jpn IT
Google · 2.6B · runs from 5.8 GB
Gemma 2 2B Jpn IT is a 2.6B-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.
TIPO V2.1 1B A200M
KBlueLeaf · 991M · runs from 0.7 GB
TIPO V2.1 1B A200M is a 991M-parameter open language model from KBlueLeaf. 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.
Qwen2.5 Coder 3B Claude Opus 4.6 Distilled
ryzdfm · 3.1B · runs from 1.7 GB
Qwen2.5 Coder 3B Claude Opus 4.6 Distilled is a 3.1B-parameter open language model from ryzdfm in the Qwen 2.5 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.
Fastino Nemotron 3.5 Lightning Healthcare
fastino · 31.6B · runs from 13.8 GB
Fastino Nemotron 3.5 Lightning Healthcare is a 31.6B-parameter open language model from fastino in the Nemotron 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.
ShellWhisperer 1.5B
fableforge-ai · 1.5B · runs from 0.8 GB
ShellWhisperer 1.5B is a 1.5B-parameter open language model from fableforge-ai. 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.