All LLM Models
Browse 982 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
Turkish Gemma 4B T1 Scout
ytu-ce-cosmos · 4.3B · runs from 2.5 GB
234
9Turkish Gemma 4B T1 Scout is a 4.3B-parameter open language model from ytu-ce-cosmos 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.
LensVLM 9B
Apple · 9.4B · runs from 3.2 GB
LensVLM-9B is Apple's research vision-language model for efficient long-document understanding, built on a 9.4-billion-parameter Qwen3.5-9B backbone. Rather than feeding a document's full text into the context window, it scans compressed images of the text and uses learned tools to selectively expand only the pages relevant to a query back into their uncompressed form, at configurable 5x, 10x, or 15x compression ratios, letting it reason over long documents while processing far less raw context per query. It is a research model released alongside its arXiv paper and reference code, not a product, and is not described as instruction-tuned for general chat. At 9.4 billion parameters it fits on a single consumer GPU, especially once quantized. Context length is 262,144 tokens. It is released under the Apple Machine Learning Research Model License, a custom license restricted strictly to non-commercial research purposes, with no commercial exploitation permitted. It was published in September 2026.
BharatGPT 3B Indic
CoRover · 3.2B · runs from 7.1 GB
BharatGPT 3B Indic is a 3.2B-parameter open language model from CoRover. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Param 1 5B
bharatgenai · 5B · runs from 10.4 GB
Param 1 5B is a 5B-parameter open language model from bharatgenai. 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.
LFM2.5 8B A1B Opus Distil
reaperdoesntknow · 8.5B · runs from 4 GB
LFM2.5 8B A1B Opus Distil is a 8.5B-parameter open language model from reaperdoesntknow in the LFM2.5 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.
GigaChat3 10B A1.8B Base
ai-sage · 11.5B · runs from 5.5 GB
GigaChat3 10B A1.8B Base is a 11.5B-parameter open language model from ai-sage. 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.
YanoljaNEXT EEVE Instruct 2.8B
yanolja · 2.8B · runs from 2.2 GB
YanoljaNEXT EEVE Instruct 2.8B is a 2.8B-parameter open language model from yanolja. It supports a context window of up to 2,048 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Internlm Chat 20B
InternLM · 20B · runs from 11.3 GB
InternLM-Chat-20B is a 20-billion-parameter chat model from a collaboration between the Shanghai AI Laboratory, SenseTime, CUHK, and Fudan University, built by applying supervised fine-tuning and RLHF on top of the InternLM-20B base model. InternLM-20B used a deliberately deep 60-layer architecture, versus the 32-40 layers typical of 7B/13B models of its era, trained on over 2.3 trillion tokens of English, Chinese, and code data, giving it stronger reasoning, math, and coding scores than contemporaries like Llama 2 13B and Baichuan2-13B. As a 20-billion-parameter dense model, it fits on a single consumer GPU once quantized. Context length is 4,096 tokens natively, extendable to about 16,384 tokens through inference-time extrapolation, per the model card. It is released under the Apache 2.0 license for the code, with model weights free for academic research and available for free commercial use after applying for a license from the developers. It was published in September 2023, predating the InternLM2 generation.
Mellum2 12B A2.5B Instruct SFT
JetBrains · 12.1B · runs from 5.5 GB
Mellum2 12B A2.5B Instruct SFT is a 12.1B-parameter open language model from JetBrains in the Mellum 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.
MIST Mini 8B Thinking
olaverse · 8.0B · runs from 4.0 GB
MIST Mini 8B Thinking is a 8.0B-parameter open language model from olaverse. 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.
SmolLM2 70M
codelion · 69M · runs from 0.4 GB
SmolLM2 70M is a 69M-parameter open language model from codelion in the SmolLM 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.
StorySupra 10M
SupraLabs · 13M · runs from 0.3 GB
StorySupra 10M is a 13M-parameter open language model from SupraLabs. It supports a context window of up to 256 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
CAT Thinking 8B
cyberagent · 8.2B · runs from 4.1 GB
CAT Thinking 8B is a 8.2B-parameter open language model from cyberagent. 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.
Mistral Small 3.2 24B Qiskit
Qiskit · 24.0B · runs from 10.9 GB
Mistral Small 3.2 24B Qiskit is a 24.0B-parameter open language model from Qiskit in the Mistral 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.
Qwen3.5 4B MiniFantasy MTP
MuXodious · 4.7B · runs from 9.8 GB
Qwen3.5 4B MiniFantasy MTP is a 4.7B-parameter open language model from MuXodious in the Qwen 3.5 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 2 Mitra E
buddhist-nlp · 9.2B · runs from 4.8 GB
Gemma 2 Mitra E is a 9.2B-parameter open language model from buddhist-nlp in the Gemma 2 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.
Instella 3B
amd · 3.1B · runs from 7.3 GB
Instella 3B is a 3.1B-parameter open language model from amd. 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.
XiaoHong V1
CongJ-Pan · 8.2B · runs from 4.1 GB
XiaoHong V1 is a 8.2B-parameter open language model from CongJ-Pan. 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.
Distil Qwen3 0.6B Text2sql
distil-labs · 596M · runs from 0.7 GB
Distil Qwen3 0.6B Text2sql is a 596M-parameter open language model from distil-labs 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.
Text2cypher Gemma 2 9B IT Finetuned 2024v1
neo4j · 9B · runs from 4.2 GB
Text2cypher Gemma 2 9B IT Finetuned 2024v1 is a 9B-parameter open language model from neo4j in the Gemma 2 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Huihui LFM2.5 8B A1B Abliterated
huihui-ai · 8.5B · runs from 4 GB
Huihui LFM2.5 8B A1B Abliterated is a 8.5B-parameter open language model from huihui-ai in the LFM2.5 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.
Granite Guardian 3.2 8B Factuality Detection
IBM · 8.2B · runs from 4.1 GB
Granite Guardian 3.2 8B Factuality Detection is a 8.2B-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.
Llamatron 8B V1
Naphula · 8.0B · runs from 4.0 GB
Llamatron 8B V1 is a 8.0B-parameter open language model from Naphula in the Llama 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.
Protgpt2 Distilled Tiny
littleworth · 39M · runs from 0.0 GB
Protgpt2 Distilled Tiny is a 39M-parameter open language model from littleworth. 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.
Nafie 473M
nafie-ai · 473M · runs from 1.0 GB
Nafie 473M is a 473M-parameter open language model from nafie-ai. 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.
Venice Uncensored
AskVenice · 23.6B · runs from 10.7 GB
Venice Uncensored is a 23.6B-parameter open language model from AskVenice. 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.
Qehwa Pashto Llm
junaid008 · 7.6B · runs from 3.6 GB
Qehwa Pashto Llm is a 7.6B-parameter open language model from junaid008. 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 Flash 3B
NVIDIA · 2.7B · runs from 6.0 GB
Nemotron Flash 3B is a 2.7B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 29,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Apex 1 Instruct 350M
LH-Tech-AI · 350M · runs from 0.8 GB
Apex 1 Instruct 350M is a 350M-parameter open language model from LH-Tech-AI. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qliphoth 12B V1.2
OccultAI · 12.2B · runs from 5.9 GB
Qliphoth 12B V1.2 is a 12.2B-parameter open language model from OccultAI. It supports a context window of up to 1,024,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.