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
Helium 1 2B
kyutai · 2.0B · runs from 1.4 GB
16.2K
52Helium 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.
Qwen3.8 27B MTPLX Optimized Quality
Youssofal · 27.4B · runs from 55.5 GB
Qwen3.8 27B MTPLX Optimized Quality is a 27.4B-parameter open language model from Youssofal 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.
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.
Qwen2 57B A14B Instruct
Alibaba · 57.4B · runs from 24.8 GB
Qwen2 57B A14B Instruct is a 57.4B-parameter open language model from Alibaba in the Qwen 2 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.
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.
Llama 2 70B HF
Meta · 69.0B · runs from 151.8 GB
Llama 2 70B HF is a 69.0B-parameter open language model from Meta in the Llama 2 family. 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.
Qwen3.8 Flash Next MTPLX Optimized Speed
Youssofal · 126.2B · runs from 54.0 GB
Qwen3.8 Flash Next MTPLX Optimized Speed is a 126.2B-parameter open language model from Youssofal 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.
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.
Bloom
BigScience · 176.2B · runs from 82.4 GB
Bloom is a 176.2B-parameter open language model from BigScience. 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.
Mixtral 8x22B v0.1
Mistral AI · 140.6B · runs from 60.5 GB
Mixtral-8x22B-v0.1 is Mistral AI's large sparse mixture-of-experts base model, a pretrained checkpoint with no instruction tuning and no built-in moderation, intended as the foundation for fine-tuned or instruct derivatives rather than direct chat use. It routes each token through 2 of 8 experts, giving roughly 39 billion active parameters out of about 141 billion total, so its per-token compute is far lighter than its total size at the cost of having to hold every expert in memory. Its pretraining data covers English, French, German, Spanish, and Italian. Because all experts must be resident even though only a fraction activate per token, it still needs a multi-GPU workstation even when quantized. Context length is 65,536 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in April 2024, ahead of an instruction-tuned Mixtral-8x22B-Instruct release.
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.
Yi 1.5 9B
01.AI · 8.8B · runs from 4.3 GB
Yi 1.5 9B is a 8.8B-parameter open language model from 01.AI in the Yi 1.5 family. 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.
Mathstral 7B v0.1
Mistral AI · 7.2B · runs from 3.6 GB
Mathstral 7B v0.1 is a 7.2B-parameter open language model from Mistral 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.
Qwen3.6 27B Uncensored HauhauCS Aggressive MTP
AIOpsInSpace · 27B · runs from 10.0 GB
Qwen3.6 27B Uncensored HauhauCS Aggressive MTP is a 27B-parameter open language model from AIOpsInSpace in the Qwen 3.6 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwopus3.6 27B Coder
Jackrong · 27.8B · runs from 56.3 GB
Qwopus3.6 27B Coder is a 27.8B-parameter open language model from Jackrong. 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.
Apodex 1.0 Mini
apodex · 36.0B · runs from 72.3 GB
Apodex 1.0 Mini is a 36.0B-parameter open language model from apodex. 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.