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
Finance Llama3 8B
instruction-pretrain · 8.0B · runs from 4.0 GB
2.0K
76Finance Llama3 8B is a 8.0B-parameter open language model from instruction-pretrain 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.
Huihui Qwen3 4B Abliterated v2
huihui-ai · 4.0B · runs from 2.2 GB
Huihui Qwen3 4B Abliterated v2 is a 4.0B-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.
UserLM 8B
Microsoft · 8.0B · runs from 4.0 GB
UserLM 8B is a 8.0B-parameter open language model from Microsoft. 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.
MediPhi Instruct
Microsoft · 3.8B · runs from 2.7 GB
MediPhi Instruct is a 3.8B-parameter open language model from Microsoft 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.
Carbon 8B
HuggingFaceBio · 8.3B · runs from 4.1 GB
Carbon 8B is a 8.3B-parameter open language model from HuggingFaceBio. 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.
Atom2.7m
UniversalComputingResearch · 3M · runs from 0.3 GB
Atom2.7m is a 3M-parameter open language model from UniversalComputingResearch. It supports a context window of up to 512 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Smol Llama 101M GQA
BEE-spoke-data · 101M · runs from 0.4 GB
Smol Llama 101M GQA is a 101M-parameter open language model from BEE-spoke-data in the Llama family. 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.
Qwen3.8 Flash Next VQ 2.1bpw
TheDrainFlorist · 24.6B · runs from 10.8 GB
Qwen3.8 Flash Next VQ 2.1bpw is a 24.6B-parameter open language model from TheDrainFlorist 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.
Qwen3 42B A3B 2507 Thinking Abliterated Uncensored TOTAL RECALL v2 Medium MASTER CODER
DavidAU · 42.4B · runs from 18.4 GB
Qwen3 42B A3B 2507 Thinking Abliterated Uncensored TOTAL RECALL v2 Medium MASTER CODER is a 42.4B-parameter open language model from DavidAU 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.
Domyn Small v1.0
domyn · 9.8B · runs from 4.7 GB
Domyn Small v1.0 is a 9.8B-parameter open language model from domyn. 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.
Qwen3.8 9B Distill Uncensored Heretic
petruhonk · 9.4B · runs from 4.6 GB
Qwen3.8 9B Distill Uncensored Heretic is a 9.4B-parameter open language model from petruhonk 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.
NEXUS Coder
fableforge-ai · 1.5B · runs from 1.0 GB
NEXUS Coder 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.
Qwen3.5 9B Uncensored
LEONW24 · 9B · runs from 4.2 GB
Qwen3.5 9B Uncensored is a 9B-parameter open language model from LEONW24 in the Qwen 3.5 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Ling 3.0 Flash Fin
Inclusion AI · 127.5B · runs from 55.4 GB
Ling 3.0 Flash Fin is a 127.5B-parameter open language model from Inclusion AI in the Ling 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.
JoyAI LLM Flash
jdopensource · 49.3B · runs from 21.9 GB
JoyAI LLM Flash is a 49.3B-parameter open language model from jdopensource. 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.
GLM 5.3 W4AFP8
PhalaCloud · 386.1B · runs from 168.3 GB
GLM 5.3 W4AFP8 is a 386.1B-parameter open language model from PhalaCloud 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.
Limite 1B Violetto
paradigma-inc · 1.0B · runs from 2.5 GB
Limite 1B Violetto is a 1.0B-parameter open language model from paradigma-inc. 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.
Gemma 4 31B StyleTune
Gryphe · 32.7B · runs from 67.0 GB
Gemma 4 31B StyleTune is a 32.7B-parameter open language model from Gryphe 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.
TLive Omni 4B
TaoLiveAIGC · 5.8B · runs from 12.1 GB
TLive Omni 4B is a 5.8B-parameter open language model from TaoLiveAIGC. 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 1.7B Abliterated
huihui-ai · 1.7B · runs from 0.8 GB
Qwen3 1.7B Abliterated is a 1.7B-parameter open language model from huihui-ai in the Qwen 3 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.8 Flash Next OQ5e Mtp
GBP-DE · 180.0B · runs from 76.9 GB
Qwen3.8 Flash Next OQ5e Mtp is a 180.0B-parameter open language model from GBP-DE 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.
Llama 3.1 Nemotron Safety Guard 8B v3
NVIDIA · 8.0B · runs from 4.0 GB
Llama 3.1 Nemotron Safety Guard 8B v3 is a 8.0B-parameter open language model from NVIDIA 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.
Gemma 4 31B IT Control Vectors
gghfez · 31B · runs from 14.5 GB
Gemma 4 31B IT Control Vectors is a 31B-parameter open language model from gghfez in the Gemma 4 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama 3 Korean Bllossom 8B
MLP-KTLim · 8.0B · runs from 4.0 GB
Llama 3 Korean Bllossom 8B is a 8.0B-parameter open language model from MLP-KTLim 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.
LongCat 2.0
Meituan · 1775.6B · runs from 3906.2 GB
LongCat-2.0 is Meituan's large-scale mixture-of-experts language model, with roughly 1.8 trillion total parameters and about 48 billion active per token, built for coding and agentic workflows and integrated with coding harnesses such as Claude Code and OpenClaw. Both its training and large-scale deployment run entirely on AI ASIC accelerator superpods rather than GPUs, with pretraining spanning more than 35 trillion tokens without rollbacks or loss spikes. Its key architectural addition, LongCat Sparse Attention, combines streaming-aware, cross-layer, and hierarchical indexing to speed up long-context inference, alongside a 135-billion-parameter N-gram embedding component that adds capacity outside the MoE layers. It was trained on hundreds of billions of tokens of million-token-context data. Given its scale, it needs a multi-GPU server even heavily quantized. Context length is 262,144 tokens. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in July 2026.
LLaDA2.2 Flash
Inclusion AI · 102.9B · runs from 206.2 GB
LLaDA2.2 Flash is a 102.9B-parameter open language model from Inclusion 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.
Nex N2.5 Mini Uncensored
orcarouter · 35.1B · runs from 16.4 GB
Nex N2.5 Mini Uncensored is a 35.1B-parameter open language model from orcarouter. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Arch Router 1.5B
katanemo · 1.5B · runs from 1.0 GB
Arch Router 1.5B is a 1.5B-parameter open language model from katanemo. 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.
FastVLM 7B
Apple · 7.8B · runs from 15.9 GB
FastVLM 7B is a 7.8B-parameter open language model from Apple. 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.
Evo2 1B Base
Aquiles-ai · 1.1B · runs from 2.4 GB
Evo2 1B Base is a 1.1B-parameter open language model from Aquiles-ai. 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.