All LLM Models
Browse 856 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
GLM 4.5 Air Derestricted
ArliAI · 110.5B · runs from 47.4 GB
172
96GLM 4.5 Air Derestricted is a 110.5B-parameter open language model from ArliAI in the GLM 4 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.
Step 3.5 Flash Base Midtrain
stepfun-ai · 197.8B · runs from 92.5 GB
Step 3.5 Flash Base Midtrain is a 197.8B-parameter open language model from stepfun-ai. 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 LFM2.5 8B A1B Abliterated
huihui-ai · 8.5B · runs from 4 GB
Huihui LFM2.5 8B A1B Abliterated is a 8.5B-parameter open language model from huihui-ai. 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.
Sarvam 30B BF16
abhinand · 32.2B · runs from 14 GB
Sarvam 30B BF16 is a 32.2B-parameter open language model from abhinand. 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 Guardian 3.2 8B Factuality Detection
IBM · 8.2B · runs from 4.1 GB
Granite Guardian 3.2 8B Factuality Detection 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.
Llamatron 8B V1
Naphula · 8.0B · runs from 4.0 GB
Llamatron 8B V1 is a 8.0B-parameter open language model from Naphula in the Llama 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.
NousCoder 14B
Nous Research · 14.8B · runs from 6.9 GB
NousCoder 14B is a 14.8B-parameter open language model from Nous Research. It supports a context window of up to 81,920 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Protgpt2 Distilled Tiny
littleworth · 39M · runs from 0.0 GB
Protgpt2 Distilled Tiny is a 39M-parameter open language model from littleworth. 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.
Nafie 473M
nafie-ai · 473M · runs from 1.0 GB
Nafie 473M is a 473M-parameter open language model from nafie-ai. 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.
STEM Oracle 27B
Verdugie · 27B · runs from 12.6 GB
STEM Oracle 27B is a 27B-parameter open language model from Verdugie. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
NVIDIA Nemotron 3 Ultra 550B A55B GenRM
NVIDIA · 560.5B · runs from 262.1 GB
NVIDIA Nemotron 3 Ultra 550B A55B GenRM is a 560.5B-parameter open language model from NVIDIA 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.
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Heretic v2
llmfan46 · 27.4B · runs from 12.4 GB
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Heretic v2 is a 27.4B-parameter open language model from llmfan46 in the Qwen 3.5 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.
Venice Uncensored
AskVenice · 23.6B · runs from 10.7 GB
Venice Uncensored is a 23.6B-parameter open language model from AskVenice. 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.
MiroThinker 1.7
miromind-ai · 235.1B · runs from 100.4 GB
MiroThinker 1.7 is a 235.1B-parameter open language model from miromind-ai. 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.
Qehwa Pashto Llm
junaid008 · 7.6B · runs from 3.6 GB
Qehwa Pashto Llm is a 7.6B-parameter open language model from junaid008. 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.
Nemotron Flash 3B
NVIDIA · 2.7B · runs from 6.0 GB
Nemotron Flash 3B is a 2.7B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 29,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Apex 1 Instruct 350M
LH-Tech-AI · 350M · runs from 0.8 GB
Apex 1 Instruct 350M is a 350M-parameter open language model from LH-Tech-AI. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qliphoth 12B V1.2
OccultAI · 12.2B · runs from 5.9 GB
Qliphoth 12B V1.2 is a 12.2B-parameter open language model from OccultAI. It supports a context window of up to 1,024,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Ouro Hybrid 1.4B
chili-lab · 1.5B · runs from 3.7 GB
Ouro Hybrid 1.4B is a 1.5B-parameter open language model from chili-lab. 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.
KernelLLM
Meta · 8.0B · runs from 4.0 GB
KernelLLM is a 8.0B-parameter open language model from Meta. 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.
OpenCodeReasoning Nemotron 1.1 32B
NVIDIA · 32.8B · runs from 14.8 GB
OpenCodeReasoning Nemotron 1.1 32B is a 32.8B-parameter open language model from NVIDIA in the Nemotron 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.
NextCoder 7B
Microsoft · 7.6B · runs from 3.6 GB
NextCoder 7B is a 7.6B-parameter open language model from Microsoft. 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.
Riva Translate 4B Instruct
NVIDIA · 4.2B · runs from 2.3 GB
Riva Translate 4B Instruct is a 4.2B-parameter open language model from NVIDIA. 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.
Meme Trix MoE 14B A8B V1
Naphula · 13.7B · runs from 6.4 GB
Meme Trix MoE 14B A8B V1 is a 13.7B-parameter open language model from Naphula. It supports a context window of up to 1,073,152 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Supra Mini V6 1M
SupraLabs · 1M · runs from 0.3 GB
Supra Mini V6 1M is a 1M-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.
ERNIE 4.5 0.3B Paddle
Baidu · 361M · runs from 1.0 GB
ERNIE 4.5 0.3B Paddle is a 361M-parameter open language model from Baidu in the ERNIE 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.
XiYanSQL QwenCoder 32B 2504
XGenerationLab · 32B · runs from 14.4 GB
XiYanSQL QwenCoder 32B 2504 is a 32B-parameter open language model from XGenerationLab 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.
OpenPangu 7B Diffusion DeepDiver
DLLM-Agent · 8.0B · runs from 16.6 GB
OpenPangu 7B Diffusion DeepDiver is a 8.0B-parameter open language model from DLLM-Agent. 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 4.7 Flash Ultimate Irrefusable Heretic
llmfan46 · 29.9B · runs from 13.8 GB
GLM 4.7 Flash Ultimate Irrefusable Heretic is a 29.9B-parameter open language model from llmfan46 in the GLM 4 family. 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.
Step 3.5 Flash REAP 121B A11B
Cerebras · 121.0B · runs from 56.5 GB
Step 3.5 Flash REAP 121B A11B is a 121.0B-parameter open language model from Cerebras. 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.