All LLM Models

Browse 1475 LLM models with VRAM requirements, quantization options, and hardware compatibility.

Featured only

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.

DFM Mimir

danish-foundation-models · 1.8B · runs from 1.3 GB

DFM Mimir is a 1.8B-parameter open language model from danish-foundation-models. 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.

DeepSeek V4 Flash 0731 Abliterated

cebeuq · 305.7B · runs from 130.3 GB

DeepSeek V4 Flash 0731 Abliterated is a 305.7B-parameter open language model from cebeuq in the DeepSeek V4 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.

Karnak 40B v1.0

Applied-Innovation-Center · 40.7B · runs from 17.7 GB

Karnak 40B v1.0 is a 40.7B-parameter open language model from Applied-Innovation-Center. 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.

Tower Plus 9B

Unbabel · 9.2B · runs from 4.8 GB

Tower Plus 9B is a 9.2B-parameter open language model from Unbabel. 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.

Goedel Prover v2 32B

Goedel-LM · 32.8B · runs from 14.6 GB

Goedel Prover v2 32B is a 32.8B-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.

Huihui Qwen3.6 27B Abliterated

huihui-ai · 27.8B · runs from 12.6 GB

Huihui Qwen3.6 27B Abliterated is a 27.8B-parameter open language model from huihui-ai 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.

Foundation Sec 8B

fdtn-ai · 8.0B · runs from 4.0 GB

Foundation Sec 8B is a 8.0B-parameter open language model from fdtn-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.

Nemotron Labs Diffusion 14B

NVIDIA · 13.5B · runs from 6.5 GB

Nemotron Labs Diffusion 14B is a 13.5B-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.

Llm Jp 3.1 1.8B Instruct4

llm-jp · 1.9B · runs from 1.5 GB

Llm Jp 3.1 1.8B Instruct4 is a 1.9B-parameter open language model from llm-jp. 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.

K2 Horizon 375B A23B

IFM · 379.2B · runs from 759.1 GB

K2 Horizon 375B A23B is a 379.2B-parameter open language model from IFM. 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.

EuroLLM 9B Instruct 2512

utter-project · 9.2B · runs from 4.5 GB

EuroLLM 9B Instruct 2512 is a 9.2B-parameter open language model from utter-project. 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 Finance

fastino · 31.6B · runs from 13.8 GB

Fastino Nemotron 3.5 Lightning Finance 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.

Quasar 3B A1B Preview

silx-ai · 2.9B · runs from 6.5 GB

Quasar 3B A1B Preview is a 2.9B-parameter open language model from silx-ai. It supports a context window of up to 16,384 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Tiny Aya Base

Cohere · 3.3B · runs from 7.4 GB

Tiny Aya Base is a 3.3B-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.

Salamandra 2B Instruct

BSC-LT · 2.3B · runs from 1.7 GB

Salamandra 2B Instruct is a 2.3B-parameter open language model from BSC-LT. 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 SFT

OpenBMB · 1.1B · runs from 0.8 GB

MiniCPM5 1B SFT 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.

Carbon 3B

HuggingFaceBio · 3.5B · runs from 1.9 GB

Carbon 3B is a 3.5B-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.

MoziAI 27B MTP

chenyumo · 27B · runs from 12.2 GB

MoziAI 27B MTP is a 27B-parameter open language model from chenyumo. 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.

Qwen3.8 27B Cold Fusion GAIN V1.1

DavidAU · 27.8B · runs from 12.6 GB

Qwen3.8 27B Cold Fusion GAIN V1.1 is a 27.8B-parameter open language model from DavidAU 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.

Qwen3.5 4B PTBR

lucasmg09 · 4B · runs from 1.5 GB

Qwen3.5 4B PTBR is a 4B-parameter open language model from lucasmg09 in the Qwen 3.5 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Txgemma 2B Predict

Google · 2.6B · runs from 1.2 GB

Txgemma 2B Predict 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.

LFM2 2.6B Longevity

Liquid AI · 2.6B · runs from 1.5 GB

LFM2 2.6B Longevity is a 2.6B-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.

Qwen3 8B Heretic

DreamFast · 8.2B · runs from 4.1 GB

Qwen3 8B Heretic is a 8.2B-parameter open language model from DreamFast 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.

Aya Expanse 32B

Cohere · 32.3B · runs from 15.1 GB

Aya Expanse 32B is Cohere Labs' 32.3-billion-parameter multilingual chat model, built on the Command-R model family and refined through data arbitrage, multilingual preference training, safety tuning, and model merging aimed at closing the performance gap between English and lower-resource languages. It is optimized to perform well across 23 languages including Arabic, Chinese, French, Hindi, Japanese, and Russian, and Cohere reported it outperforming much larger models such as Llama 3.1 405B and Mistral Large 2 on multilingual evaluation. At 32.3 billion parameters, it needs a high-end consumer GPU or multi-GPU setup once quantized. It is released under the CC BY-NC 4.0 license, restricting use to non-commercial purposes only, and was published in October 2024, as the 32B counterpart to the smaller Aya Expanse 8B model.

SIQ 1 35B

AlexWortega · 34.7B · runs from 15.1 GB

SIQ 1 35B is a 34.7B-parameter open language model from AlexWortega. 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.

Hypernova 60B 2605

MultiverseComputingCAI · 58.7B · runs from 25.3 GB

Hypernova 60B 2605 is a 58.7B-parameter open language model from MultiverseComputingCAI. 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.

Tri 21B Think

trillionlabs · 20.7B · runs from 42.2 GB

Tri 21B Think is a 20.7B-parameter open language model from trillionlabs. 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.

SILMA 9B Instruct v1.0

silma-ai · 9.2B · runs from 4.8 GB

SILMA 9B Instruct v1.0 is a 9.2B-parameter open language model from silma-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.

Baichuan2 7B Base

baichuan-inc · 7B · runs from 3.3 GB

Baichuan2-7B-Base is Baichuan Intelligence's second-generation 7-billion-parameter pretrained base model, a bilingual English/Chinese language model, not instruction-tuned, trained on 2.6 trillion tokens of high-quality data, up from 1.2 trillion for the original Baichuan-7B. It reports the best results among same-size open models on Chinese and English benchmarks including C-Eval, MMLU, CMMLU, and BBH. A separately released Baichuan2-7B-Chat provides the aligned, conversational counterpart to this base checkpoint, along with a 4-bit quantized chat variant. At 7 billion parameters it runs easily on a single consumer GPU. Context length is 4,096 tokens. It is released under a custom Baichuan2 Community License plus Apache 2.0 for the code: free for research, and free for commercial use only for organizations with under 1 million daily active users that are not themselves software or cloud service providers, subject to a written authorization request. It was published in August 2023.

Qwen3.6 27B MTPLX Optimized

Youssofal · 26.9B · runs from 12.2 GB

Qwen3.6 27B MTPLX Optimized is a 26.9B-parameter open language model from Youssofal 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.