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
Qwen3.8 Flash Next 40B Prune Research
Davd-b01 · 40.7B · runs from 17.7 GB
1.2K
2Qwen3.8 Flash Next 40B Prune Research is a 40.7B-parameter open language model from Davd-b01 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.
MiniMax M3 EAGLE3 GQA
Inferact · 3.1B · runs from 1.6 GB
MiniMax M3 EAGLE3 GQA is a 3.1B-parameter open language model from Inferact in the MiniMax 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.
Grug 12B
kai-os · 12.0B · runs from 25.0 GB
Grug 12B is a 12.0B-parameter open language model from kai-os. 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.
Qwen35 4B Soyuz Merged
AlexWortega · 4B · runs from 8.5 GB
Qwen35 4B Soyuz Merged is a 4B-parameter open language model from AlexWortega in the Qwen 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.
Fable Coder 35B A3B
Achilles1089 · 36.0B · runs from 72.3 GB
Fable Coder 35B A3B is a 36.0B-parameter open language model from Achilles1089. 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.
Puro 2B Base
thu-pacman · 2.0B · runs from 1.4 GB
Puro 2B Base is a 2.0B-parameter open language model from thu-pacman. 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.
Evo2 7B
Aquiles-ai · 6.6B · runs from 14.5 GB
Evo2 7B is a 6.6B-parameter open language model from Aquiles-ai. 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.
Raptor 0.6 4B JANG 6M
OsaurusAI · 4.1B · runs from 8.7 GB
Raptor 0.6 4B JANG 6M is a 4.1B-parameter open language model from OsaurusAI. 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.
NCP ArchPreview Dolma3 8.9B Stage1
ArchSpace-Collection · 8.9B · runs from 19.7 GB
NCP ArchPreview Dolma3 8.9B Stage1 is a 8.9B-parameter open language model from ArchSpace-Collection. 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.
Macaron V1 Preview 749B
mindlab-research · 753.9B · runs from 1512.0 GB
Macaron V1 Preview 749B is a 753.9B-parameter open language model from mindlab-research. It supports a context window of up to 202,752 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Soren 1 Small
syntropy-ai · 1.9B · runs from 4.2 GB
Soren 1 Small is a 1.9B-parameter open language model from syntropy-ai. 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.
Qwen3.6 27B AEON Ultimate Uncensored BF16
AEON-7 · 27.4B · runs from 55.5 GB
Qwen3.6 27B AEON Ultimate Uncensored BF16 is a 27.4B-parameter open language model from AEON-7 in the Qwen 3.6 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.
Kimi K2.6 Dspark
novita · 3.1B · runs from 1.5 GB
Kimi K2.6 Dspark is a 3.1B-parameter open language model from novita in the Kimi K2 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Grug 35B A3B
kai-os · 34.7B · runs from 69.7 GB
Grug 35B A3B is a 34.7B-parameter open language model from kai-os. 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.
Parable Granite 4.1 8B Claude Fable 5
AnkitAI · 8.4B · runs from 4.2 GB
Parable Granite 4.1 8B Claude Fable 5 is a 8.4B-parameter open language model from AnkitAI 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.
GPT OSS 20B Heretic Ara v3
p-e-w · 21.5B · runs from 9.5 GB
GPT OSS 20B Heretic Ara v3 is a 21.5B-parameter open language model from p-e-w 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.
Hunyuan 0.5B Pretrain
Tencent · 539M · runs from 0.6 GB
Hunyuan 0.5B Pretrain is a 539M-parameter open language model from Tencent in the Hunyuan 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.
Raptor V0.5 8B A1B JANG 6M
OsaurusAI · 6.2B · runs from 12.9 GB
Raptor V0.5 8B A1B JANG 6M is a 6.2B-parameter open language model from OsaurusAI. 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.
Orca Mini 3B
pankajmathur · 3.4B · runs from 1.6 GB
Orca Mini 3B is a 3.4B-parameter open language model from pankajmathur in the Orca 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.
GLM 5.3 EXL3 TR3 3.42bpw
davidsyoung · 177.5B · runs from 79.7 GB
GLM 5.3 EXL3 TR3 3.42bpw is a 177.5B-parameter open language model from davidsyoung in the GLM 5 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.
Diffusiongemma 26B A4B IT Q4 K M Layers
meshllm · 26B · runs from 12.2 GB
Diffusiongemma 26B A4B IT Q4 K M Layers is a 26B-parameter open language model from meshllm in the DiffusionGemma family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Grug 27B
ProCreations · 27.4B · runs from 55.5 GB
Grug 27B is a 27.4B-parameter open language model from ProCreations. 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.
Ternary Bonsai 27B Antidoom DSpark
Danny-Dasilva · 27B · runs from 12.6 GB
Ternary Bonsai 27B Antidoom DSpark is a 27B-parameter open language model from Danny-Dasilva. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
ViAble 1.7 9B
bogairff55 · 9.0B · runs from 18.5 GB
ViAble 1.7 9B is a 9.0B-parameter open language model from bogairff55. 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.
GLM 5.3 EXL3 TR3 3.25bpw
davidsyoung · 169.6B · runs from 76.3 GB
GLM 5.3 EXL3 TR3 3.25bpw is a 169.6B-parameter open language model from davidsyoung in the GLM 5 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.
WebWorld 8B
Alibaba · 8.2B · runs from 4.1 GB
WebWorld 8B is a 8.2B-parameter open language model from Alibaba. 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.
ToolWeave Stage3
muradil211 · 4.4B · runs from 2.4 GB
ToolWeave Stage3 is a 4.4B-parameter open language model from muradil211. 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.
Minicpm5 2B Distilled Reasoning
jigs97022 · 2.5B · runs from 1.5 GB
Minicpm5 2B Distilled Reasoning is a 2.5B-parameter open language model from jigs97022 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.
T Pro IT 2.1
t-tech · 32.8B · runs from 14.6 GB
T Pro IT 2.1 is a 32.8B-parameter open language model from t-tech. 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.
LFM2 350M Extract
Liquid AI · 354M · runs from 0.5 GB
LFM2 350M Extract is a 354M-parameter open language model from Liquid AI in the LFM2 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.