All LLM Models

Browse 1242 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.

OneReason 0.8B Pretrain Competition

OpenOneRec · 801M · runs from 0.8 GB

OneReason 0.8B Pretrain Competition is a 801M-parameter open language model from OpenOneRec. 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.

Qwen3.6 27B MTPLX Optimized Speed

Youssofal · 4.7B · runs from 2.7 GB

Qwen3.6 27B MTPLX Optimized Speed is a 4.7B-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.

Nemotron Cascade 8B

NVIDIA · 8B · runs from 4 GB

Nemotron Cascade 8B is a 8B-parameter open language model from NVIDIA in the Nemotron 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.

MiniCPM 2B Sft BF16

OpenBMB · 2B · runs from 1.9 GB

MiniCPM 2B Sft BF16 is a 2B-parameter open language model from OpenBMB in the MiniCPM 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.

Falcon 7B Instruct

TII UAE · 7.2B · runs from 3.4 GB

Falcon 7B Instruct is the instruction-tuned version of TII's Falcon 7B, fine-tuned on a mix of chat and instruction datasets to follow user prompts more reliably. It was among the early open models to show that a well-tuned 7B model could handle conversational tasks, summarization, and basic reasoning without requiring massive hardware. While newer models have since raised the bar, Falcon 7B Instruct remains a lightweight option for users who want a responsive local assistant with modest resource requirements.

Codegemma 2B

Google · 2.5B · runs from 1.2 GB

Codegemma 2B is a 2.5B-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.

Gemma 7B IT

Google · 8.5B · runs from 18.8 GB

Google Gemma 7B IT is a 7-billion parameter instruction-tuned model from the original Gemma generation. It is fine-tuned for conversational use and general instruction following, running efficiently on consumer GPUs with 8GB or more of VRAM. As a first-generation Gemma model, it has been superseded by Gemma 2 and Gemma 3 models in quality and capability, but it remains well-supported by inference frameworks. Released under the Gemma license.

Llm Jp 3.1 13B Instruct4

llm-jp · 13.7B · runs from 7.8 GB

Llm Jp 3.1 13B Instruct4 is a 13.7B-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.

ERNIE 4.5 0.3B PT

Baidu · 361M · runs from 0.5 GB

ERNIE 4.5 0.3B PT 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.

Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled

lordx64 · 36.0B · runs from 15.7 GB

Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled is a 36.0B-parameter open language model from lordx64 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.

Llama 2 13B HF

Meta · 13.0B · runs from 6.1 GB

Llama-2-13b-hf is Meta's 13-billion-parameter base (pretrained, not instruction-tuned) language model from the original Llama 2 family, intended as a general-purpose foundation for natural-language generation and further fine-tuning rather than direct assistant-style chat, for which Meta released separate Llama-2-Chat checkpoints. It is an auto-regressive transformer trained on 2 trillion tokens of publicly available data with a September 2022 knowledge cutoff, using a global batch size of 4 million tokens; unlike the 70B model, the 13B size does not use grouped-query attention. It is a historically significant open-weight release rather than a current state-of-the-art model by 2026 standards. At 13 billion parameters, it fits on a single consumer GPU once quantized. Context length is 4,096 tokens. It is released under the Llama 2 Community License, a custom license that is free for most commercial and research use but requires organizations with more than 700 million monthly active users to request separate permission from Meta. It was published in July 2023.

C4ai Command R7b 12 2024

Cohere · 8.0B · runs from 17.7 GB

C4ai Command R7b 12 2024 is a 8.0B-parameter open language model from Cohere in the Command R family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

OCC RAG 1.7B

occ-ai · 1.7B · runs from 1.3 GB

OCC RAG 1.7B is a 1.7B-parameter open language model from occ-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.

Gemma 4 12B OBLITERATED

OBLITERATUS · 12.0B · runs from 6.1 GB

Gemma 4 12B OBLITERATED is a 12.0B-parameter open language model from OBLITERATUS in the Gemma 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.

Gemma 7B

Google · 8.5B · runs from 18.8 GB

Google Gemma 7B is a 7-billion parameter base (pretrained) model from the original Gemma generation, Google's first openly available family of language models. It represents Google's initial entry into the open-weight LLM space. While superseded by Gemma 2 and Gemma 3 in terms of benchmark performance, the original Gemma 7B remains a solid foundation model and a useful reference point in the evolution of Google's open models. Released under the Gemma license.

CodeLlama 34B HF

Meta · 33.7B · runs from 15.0 GB

CodeLlama 34B HF is a 33.7B-parameter open language model from Meta in the Code Llama family. 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.

Gemma 2B IT

Google · 2.5B · runs from 1.2 GB

Gemma 2B IT is a 2.5B-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.

Baichuan 7B

baichuan-inc · 7B · runs from 15.4 GB

Baichuan-7B is Baichuan Intelligent Technology's open-source base pretrained language model, not instruction-tuned, with 7 billion parameters trained on around 1.2 trillion bilingual Chinese-English tokens. It follows a LLaMA-like Transformer design with rotary position embeddings, SwiGLU feedforward layers, and RMSNorm pre-normalization, and was positioned at release as state of the art among models of its size on the Chinese C-Eval and English MMLU benchmarks. Its 7B size makes it easy to run on a single consumer GPU. Context length is 4,096 tokens. It is released under the custom Baichuan-7B license, which is more permissive than LLaMA's original license and explicitly allows commercial use. It was published in June 2023, as one of the earliest fully open Chinese-English base models; Baichuan later released larger and instruction-tuned successors.

Ouro 1.4B

ByteDance · 1.4B · runs from 3.6 GB

Ouro 1.4B is a 1.4B-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.

Huginn 0125

tomg-group-umd · 3.9B · runs from 8.6 GB

Huginn 0125 is a 3.9B-parameter open language model from tomg-group-umd. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

ChatCodeMathReasoning

Granite 4.2 30B

IBM · 29.3B · runs from 13.3 GB

Granite 4.2 30B is a 29.3B-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.

Deepseek Moe 16B Chat

DeepSeek · 16.4B · runs from 7.7 GB

Deepseek Moe 16B Chat is a 16.4B-parameter open language model from DeepSeek in the DeepSeek 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.

Olmo Hybrid 7B

Allen AI · 7B · runs from 15.3 GB

Olmo Hybrid 7B is a 7B-parameter open language model from Allen AI in the OLMo 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.

MiniMax M3 EAGLE3

Inferact · 3.3B · runs from 1.7 GB

MiniMax M3 EAGLE3 is a 3.3B-parameter open language model from Inferact in the MiniMax 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.

Functiongemma 270M IT

Google · 268M · runs from 0.6 GB

Functiongemma 270M IT is a 268M-parameter open language model from Google in the Gemma family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Deepseek Llm 7B Chat

DeepSeek · 7B · runs from 4.3 GB

Deepseek Llm 7B Chat is a 7B-parameter open language model from DeepSeek in the DeepSeek 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.

Phi 3 Small 8k Instruct

Microsoft · 7.4B · runs from 15.3 GB

Phi-3-Small-8K-Instruct is Microsoft's 7-billion-parameter instruction-tuned chat model from the Phi-3 family, trained on a mix of synthetic data and heavily filtered public web text chosen for high reasoning density, then post-trained with supervised fine-tuning and direct preference optimization. It targets memory- and compute-constrained, latency-sensitive deployments while still emphasizing strong code, math, and logical reasoning, and Microsoft reports it holds up well against same-size and next-size-up models on common-sense, language, math, code, and long-context benchmarks. It sits alongside Mini and Medium-sized Phi-3 variants, plus a 128K-context Small sibling. At around 7 billion parameters it runs comfortably on a single consumer GPU. Context length is 8,192 tokens, as the name indicates. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in May 2024.

Starcoder

BigCode · 15.8B · runs from 7.4 GB

Starcoder is a 15.8B-parameter open language model from BigCode in the StarCoder family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Tongyi DeepResearch 30B A3B

Alibaba-NLP · 30.5B · runs from 13.4 GB

Tongyi DeepResearch 30B A3B is a 30.5B-parameter open language model from Alibaba-NLP. 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.

LFM2 350M

Liquid AI · 354M · runs from 0.5 GB

LFM2 350M is a 354M-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.