All LLM Models
Browse 1214 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
MagicPrompt Stable Diffusion
Gustavosta · 137M · runs from 0.1 GB
19.4K
741MagicPrompt Stable Diffusion is a 137M-parameter open language model from Gustavosta. 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.
Qwen1.5 4B
Alibaba · 4.0B · runs from 2.8 GB
Qwen1.5 4B is a 4.0B-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.
Zeta 2.1
zed-industries · 8.3B · runs from 4.1 GB
Zeta 2.1 is a 8.3B-parameter open language model from zed-industries. 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.
Gemma 4 26B A4B IT DFlash
z-lab · 26B · runs from 11.4 GB
Gemma 4 26B A4B IT DFlash is a 26B-parameter open language model from z-lab in the Gemma 4 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.
Gemma 4 31B IT DFlash
z-lab · 31B · runs from 13.5 GB
Gemma 4 31B IT DFlash is a 31B-parameter open language model from z-lab in the Gemma 4 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.
Qwen3 4B Z Image Engineer V4
BennyDaBall · 4B · runs from 1.9 GB
Qwen3 4B Z Image Engineer V4 is a 4B-parameter open language model from BennyDaBall in the Qwen 3 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Aya 23 8B
Cohere · 8.0B · runs from 17.7 GB
Aya 23 8B is a 8.0B-parameter open language model from Cohere in the Aya family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Unsloth Ornith 1.5 35B A3B
peculiar-ragdoll · 35B · runs from 14.9 GB
Unsloth Ornith 1.5 35B A3B is a 35B-parameter open language model from peculiar-ragdoll in the Ornith family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.8 9B Distill
empero-ai · 9.7B · runs from 4.7 GB
Qwen3.8 9B Distill is a 9.7B-parameter open language model from empero-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.
LocoOperator 4B
LocoreMind · 4.0B · runs from 2.2 GB
LocoOperator 4B is a 4.0B-parameter open language model from LocoreMind. 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.
Llm Jp 4 33B Thinking
llm-jp · 33.2B · runs from 15.0 GB
Llm Jp 4 33B Thinking is a 33.2B-parameter open language model from llm-jp. 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.
Helium 1 2B
kyutai · 2.0B · runs from 1.4 GB
Helium 1 2B is a 2.0B-parameter open language model from kyutai. 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.
Gemma 3 12B IT Heretic
DreamFast · 12.2B · runs from 6.2 GB
Gemma 3 12B IT Heretic is a 12.2B-parameter open language model from DreamFast in the Gemma 3 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.
DeepHat V1 7B
DeepHat · 7.6B · runs from 3.6 GB
DeepHat V1 7B is a 7.6B-parameter open language model from DeepHat. 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.
GLM 5.2 Speculator.dspark
RedHatAI · 3.8B · runs from 1.8 GB
GLM 5.2 Speculator.dspark is a 3.8B-parameter open language model from RedHatAI in the GLM 5 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.8 4B
empero-ai · 4.7B · runs from 2.5 GB
Qwen3.8 4B is a 4.7B-parameter open language model from empero-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.
Ektome Qwen3.8 27B PristinelyUncensored
Zynerji · 27.4B · runs from 12.4 GB
Ektome Qwen3.8 27B PristinelyUncensored is a 27.4B-parameter open language model from Zynerji 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.
Mistral Small 24B Instruct 2501 Quantized.w8a8
RedHatAI · 23.6B · runs from 10.7 GB
Mistral Small 24B Instruct 2501 Quantized.w8a8 is a 23.6B-parameter open language model from RedHatAI 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.
Hermes 2 Pro Llama 3 8B
Nous Research · 8.0B · runs from 4.0 GB
Hermes 2 Pro Llama 3 8B is a 8.0B-parameter open language model from Nous Research 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.
Qwen27b Abliterated Fable MTP
hotdogs · 27B · runs from 12.6 GB
Qwen27b Abliterated Fable MTP is a 27B-parameter open language model from hotdogs in the Qwen family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Moondream1
vikhyatk · 1.9B · runs from 4.1 GB
Moondream1 is a 1.9B-parameter open language model from vikhyatk. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.6 27B OBLITERATED
OBLITERATUS · 26.9B · runs from 12.2 GB
Qwen3.6 27B OBLITERATED is a 26.9B-parameter open language model from OBLITERATUS 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.
AFM 4.5B
Arcee AI · 4.6B · runs from 2.4 GB
AFM 4.5B is a 4.6B-parameter open language model from Arcee AI. 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.
Llama 3.1 8B Lexi Uncensored v2
Orenguteng · 8.0B · runs from 4.0 GB
Llama 3.1 8B Lexi Uncensored v2 is a 8.0B-parameter open language model from Orenguteng in the Llama 3 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.
Llama 3.2 Korean Bllossom 3B
Bllossom · 3.2B · runs from 1.9 GB
Llama 3.2 Korean Bllossom 3B is a 3.2B-parameter open language model from Bllossom in the Llama 3 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.
Qwen3.6 27B PRISM PRO DQ
Ex0bit · 27B · runs from 12.6 GB
Qwen3.6 27B PRISM PRO DQ is a 27B-parameter open language model from Ex0bit in the Qwen 3.6 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
GLM 4 9B 0414
Z.ai · 9.4B · runs from 4.4 GB
GLM 4 9B 0414 is a 9.4B-parameter open language model from Z.ai in the GLM 4 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.
Aya Expanse 8B
Cohere · 8.0B · runs from 17.7 GB
Aya Expanse 8B is a 8.0B-parameter open language model from Cohere in the Aya family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Ouro 2.6B Thinking
ByteDance · 2.7B · runs from 6.4 GB
Ouro 2.6B Thinking 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.
Qwen3.8 4B Distill
empero-ai · 4.7B · runs from 2.5 GB
Qwen3.8 4B Distill is a 4.7B-parameter open language model from empero-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.