All LLM Models

Browse 60 LLM models with VRAM requirements, quantization options, and hardware compatibility.

Featured only

Gemma 4 E4B

Google · 8.0B · runs from 5.6 GB at Q4

Gemma 4 E4B is Google DeepMind's second-smallest model in the Gemma 4 family, a dense architecture with roughly 8 billion total parameters, of which Google describes about 4.5 billion as its effective footprint at inference. This is the pretrained base checkpoint rather than an instruction-tuned model, meant for fine-tuning rather than direct chat use. Like the rest of the family it is multimodal — text, image, and natively audio at this size — targeting efficient on-device deployment on laptops and higher-end phones. It runs comfortably on a single consumer GPU, or on-device once quantized. It supports a 131,072 token context window. It carries Google's Gemma 4 license terms, published as Apache 2.0 on Hugging Face with additional Gemma-specific usage terms linked from the card. Published in March 2026, it sits between the E2B on-device model and the larger 12B, 26B-A4B, and 31B tiers.

Gemma 4 12B

Google · 12.0B · runs from 9.0 GB at Q4

Gemma 4 12B Unified is a base checkpoint in Google DeepMind's Gemma 4 family, an open-weight multimodal model with roughly 12 billion parameters that takes text, image, and audio input and produces text output. Its "Unified" design skips separate encoders per modality, projecting raw image patches and audio directly into the language model, cutting multimodal latency. As a pretrained release, it's a base for fine-tuning or research rather than direct chat use. It supports a 256K token context window and multilingual pretraining across 140+ languages, and is released under the Apache 2.0 license. At roughly 12 billion parameters, it runs on a single consumer GPU with around 8-12 GB of VRAM once quantized to 4-bit.

Gemma 4 31B

Google · 31.3B · runs from 21.7 GB at Q4

Gemma 4 31B is Google DeepMind's largest dense model in the Gemma 4 family, roughly 32.7 billion parameters, handling text and image input. This is the pretrained base checkpoint rather than an instruction-tuned model, meant as a foundation for fine-tuning rather than direct chat use. Gemma 4 introduces a hybrid attention design interleaving local sliding-window attention with occasional full global attention, plus configurable reasoning modes. At this size, local inference needs a high-end consumer or prosumer GPU, especially once quantized. It supports a 262,144 token context window, among the largest in the family. It carries Google's Gemma 4 license terms, published as Apache 2.0 on Hugging Face with additional Gemma-specific usage terms linked from the card. Published in March 2026, it is the largest of five Gemma 4 sizes (E2B, E4B, 12B, 26B-A4B MoE, 31B dense).

Gemma 3 270M

Google · 268M · runs from 1.2 GB at Q4

Google Gemma 3 270M is a 270-million parameter base (pretrained) model from Google's Gemma 3 family. It is an experimental release intended for research, fine-tuning, and exploring the capabilities of ultra-small language models. The model runs on virtually any hardware with negligible resource requirements. Released under the Gemma license.

Gemma 4 31B IT Qat Q4 0 Unquantized Assistant

Google · 31B · runs from 19.0 GB at Q4

Gemma 4 31B IT Qat Q4 0 Unquantized Assistant is a 31B-parameter open language model from Google 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 8.2 GB at Q4

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.

Gemma 2B

Google · 2.5B · runs from 3.5 GB at Q4

Gemma 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 3 4B Pt

Google · 4.3B · runs from 5 GB at Q4

Gemma 3 4B PT represents Google's pretrained checkpoint at the lower end of the Gemma 3 family, containing roughly 4.3 billion parameters when vision components are included. This model employs a vision-language architecture capable of handling both text and images. The "PT" suffix indicates its status as a base model: it lacks instruction tuning and cannot reliably follow chat prompts, making it suitable for fine-tuning, research, or experimentation instead of direct use as an assistant. Given its size, the quantized version runs on nearly any recent GPU or even a CPU, though the instruction-tuned release remains the better choice for actual conversation. Similar to the larger Gemma 3 models, it supports a context window of up to 128K tokens. Distribution follows the Gemma Terms of Use, and users must acknowledge this license on Hugging Face to gain access. Released in February 2025, it stands as one of the smaller pretrained options within the Gemma 3 lineup, sitting alongside the 12B and 27B variants.

Codegemma 7B IT

Google · 8.5B · runs from 8.2 GB at Q4

Codegemma 7B IT is a 8.5B-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.

Shieldgemma 9B

Google · 9.2B · runs from 8.8 GB at Q4

Shieldgemma 9B is a 9.2B-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.

Gemma 3 12B Pt

Google · 12.2B · runs from 10.9 GB at Q4

Gemma 3 12B PT is Google's roughly 12-billion-parameter pretrained checkpoint in the Gemma 3 family, built on a vision-language architecture that accepts both text and images. The PT suffix marks the base model: it lacks instruction tuning and doesn't handle chat prompts well, so it serves as a starting point for fine-tuning or research instead of direct use as an assistant. Hugging Face lists this version as image-text-to-text. At this size it fits on a single consumer GPU once quantized, while the instruction-tuned variant remains the standard choice for conversation. It supports a 128K-token context window. Distribution follows the Gemma Terms of Use, and access requires acknowledging the license on Hugging Face. Released in March 2025, it falls between the 4B and 27B models within the Gemma 3 lineup.

Gemma 3 1B Pt

Google · 1000M · runs from 2.1 GB at Q4

Gemma 3 1B Pt is a 1000M-parameter open language model from Google in the Gemma 3 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Gemma 2 2B

Google · 2.6B · runs from 3.6 GB at Q4

Google Gemma 2 2B is a 2-billion parameter base (pretrained) model from Google's Gemma 2 family. As a base model, it is not instruction-tuned and is intended for fine-tuning, research, and custom downstream applications. Its compact size makes it suitable for experimentation, rapid prototyping, and domain-specific fine-tuning on consumer hardware with minimal VRAM. Released under the Gemma license.

Gemma 1.1 2B IT

Google · 2.5B · runs from 3.5 GB at Q4

Gemma 1.1 2B IT is a 2.5B-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.

Gemma 4 12B IT Assistant

Google · 12B · runs from 7.6 GB at Q4

Gemma 4 12B IT Assistant is a 12B-parameter open language model from Google 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.

T5gemma 2B 2B Ul2 IT

Google · 5.6B · runs from 6.0 GB at Q4

T5gemma 2B 2B Ul2 IT is a 5.6B-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.

T5gemma S S Prefixlm

Google · 313M · runs from 1.3 GB at Q4

T5gemma S S Prefixlm is a 313M-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.

Gemma 2 9B

Google · 9.2B · runs from 8.8 GB at Q4

Gemma 2 9B is a 9.2B-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.

Codegemma 2B

Google · 2.5B · runs from 3.5 GB at Q4

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 2B IT

Google · 2.5B · runs from 3.5 GB at Q4

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.

Functiongemma 270M IT

Google · 268M · runs from 1.2 GB at Q4

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.

Gemma 3n E4B IT Litert Lm

Google · 4B · runs from 4.8 GB at Q4

Gemma 3n E4B IT Litert Lm is a 4B-parameter open language model from Google in the Gemma 3 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

T5gemma 2B 2B Ul2

Google · 5.6B · runs from 6.0 GB at Q4

T5gemma 2B 2B Ul2 is a 5.6B-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.

Gemma 2 2B Jpn IT

Google · 2.6B · runs from 3.6 GB at Q4

Gemma 2 2B Jpn IT 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.

Txgemma 2B Predict

Google · 2.6B · runs from 3.6 GB at Q4

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.

Gemma 3n E2B IT Litert Lm

Google · 2B · runs from 3.1 GB at Q4

Gemma 3n E2B IT Litert Lm is a 2B-parameter open language model from Google in the Gemma 3 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Shieldgemma 2B

Google · 2.6B · runs from 3.6 GB at Q4

Shieldgemma 2B 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.

Vaultgemma 1B

Google · 1.0B · runs from 2.1 GB at Q4

Vaultgemma 1B is a 1.0B-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.

T5gemma L L Ul2 IT

Google · 1.2B · runs from 2.3 GB at Q4

T5gemma L L Ul2 IT is a 1.2B-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.

T5gemma B B Ul2 IT

Google · 591M · runs from 1.6 GB at Q4

T5gemma B B Ul2 IT is a 591M-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.

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.