All LLM Models

Browse 982 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.

Baichuan2 13B Chat

baichuan-inc · 13B · runs from 3.9 GB

Baichuan2-13B-Chat is Baichuan Intelligence's 13-billion-parameter bilingual (Chinese/English) chat model, instruction-aligned from the Baichuan2-13B-Base model that was pretrained from scratch on 2.6 trillion tokens. It was evaluated across general, legal, medical, math, code, and multilingual-translation benchmarks against contemporaries like LLaMA2-13B-Chat and Vicuna-13B, and a 4-bit quantized version is also distributed for lower-memory deployment. At 13B parameters it needs a capable consumer GPU at full precision, considerably less once quantized to 4 bits. License is a custom Baichuan2 Community License: free for academic research, and free for commercial use after obtaining a license via email request to the developers. It was published in August 2023, with a v2 revision issued in December 2023 that improved math, logical reasoning, and instruction-following.

Falcon H1 0.5B Base

TII UAE · 521M · runs from 0.5 GB

Falcon H1 0.5B Base is a 521M-parameter open language model from TII UAE in the Falcon 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.

OLMo 2 0425 1B

Allen AI · 1.5B · runs from 1.2 GB

OLMo 2 1B is Allen AI's smallest base language model in the OLMo 2 family, a 1.48-billion-parameter dense transformer trained on 4 trillion tokens. This is the raw pretrained checkpoint, not an instruction-tuned assistant — Allen AI releases separate SFT, DPO, and RLVR1 versions for chat use. Unusually for an open-weight release, Allen AI also publishes the training data, code, and intermediate checkpoints, making it a reference point for reproducible LLM research. At 1.48B parameters it runs comfortably on modest hardware, even unquantized. It supports a 4,096 token context window, short by current standards. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in April 2025, it is the smallest of four OLMo 2 sizes (1B, 7B, 13B, 32B) sharing the same training recipe and fully open data pipeline.

TwIL LM3

webAI-Official · 3.1B · runs from 1.5 GB

TwIL LM3 is a 3.1B-parameter open language model from webAI-Official. 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.

Dots.ocr

dots-studio · 3.0B · runs from 1.6 GB

dots.ocr is a 3-billion-parameter vision-language model built around a compact 1.7-billion-parameter language backbone, purpose-built for multilingual document layout parsing and OCR. It unifies layout detection and text recognition in one model, switching tasks — table extraction, formula recognition, reading order — by changing the prompt, instead of chaining separate detection models. Despite its small footprint, its developers report state-of-the-art results on document-parsing benchmarks, including strong performance on low-resource languages. It runs comfortably on a single consumer GPU. Context length is 131,072 tokens, ample for long documents. It is released under the MIT license, a highly permissive option for commercial use. Published in July 2025, it shows a compact single VLM can rival dedicated layout-detection models like DocLayout-YOLO.

Kimi K3 DSpark

RadixArk · 2.2B · runs from 1.3 GB

Kimi K3 DSpark is a 2.2B-parameter open language model from RadixArk in the Kimi K3 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.

Gemma 4 E2B IT Qat Q4 0 Unquantized Heretic

coder3101 · 5.1B · runs from 2.5 GB

Gemma 4 E2B IT Qat Q4 0 Unquantized Heretic is a 5.1B-parameter open language model from coder3101 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.

Qwen3.5 4B Base

Alibaba · 4.7B · runs from 2.5 GB

Qwen3.5-4B-Base is a 4.7-billion-parameter dense checkpoint in Alibaba's Qwen3.5 base family, a native vision-language foundation model trained with early fusion of image and text tokens rather than a text model with a bolted-on vision tower. It is pretrained-only weights meant for fine-tuning or research, not direct conversation, though its control tokens support efficient LoRA-style adaptation with the official chat template. It uses the same hybrid Gated DeltaNet plus gated-attention architecture as its siblings. At under 5B parameters, it runs comfortably on a single mainstream consumer GPU. Context length is a native 262,144 tokens, extensible up to 1,010,000 tokens. It is released under the Apache 2.0 license, and was published in February 2026. It sits mid-lineup among five Qwen3.5-Base sizes, between the 2B and 9B dense checkpoints, with a 35B mixture-of-experts variant at the top.

DeepSeek OCR

DeepSeek · 3.3B · runs from 1.8 GB

DeepSeek OCR is a 3.3-billion-parameter vision-language model from DeepSeek, purpose-built for optical character recognition and document parsing rather than general chat. It pairs a vision encoder with a Mixture-of-Experts decoder that activates roughly 1.1 billion parameters per token, keeping decoding fast while all expert weights still need to fit in memory. Its core idea is compressing a page of text into a much smaller set of image tokens before decoding, and it is small enough to run on a single consumer GPU once quantized. Context length is limited to 8,192 tokens, reflecting its page-oriented use case. It is released under the MIT license, a highly permissive option for commercial use, and was published in October 2025, introducing "optical context compression" to shrink the token count needed for OCR.

Qwen2.5 7B Instruct Uncensored

Orion-zhen · 7.6B · runs from 3.6 GB

Qwen2.5 7B Instruct Uncensored is a 7.6B-parameter open language model from Orion-zhen in the Qwen 2.5 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.

Qwen3.5 9B Base

Alibaba · 9.7B · runs from 4.7 GB

Qwen3.5-9B-Base is the largest dense checkpoint in Alibaba's Qwen3.5 base family, at 9.7 billion parameters, a native vision-language foundation model trained with early fusion of image and text tokens. It is pretrain-only, meant for fine-tuning or research rather than direct interaction, though its control tokens are compatible with the official chat template for LoRA-style adaptation. It shares the family's hybrid design, alternating Gated DeltaNet linear attention with periodic gated full-attention layers, at a larger hidden size than its smaller siblings. At just under 10B parameters, it needs a single mainstream-to-high-end consumer GPU once quantized. Context length is a native 262,144 tokens, extensible up to 1,010,000 tokens. It is released under the Apache 2.0 license, and was published in February 2026. Above it sits only the 35B mixture-of-experts Qwen3.5-Base model, which activates roughly 3 billion parameters per token.

SmolLM2 1.7B

Hugging Face · 1.7B · runs from 1.4 GB

SmolLM2 1.7B is the base pretrained model from Hugging Face's second-generation SmolLM family. Unlike the instruct variant, this model has not been fine-tuned for chat or instruction following, making it a strong foundation for custom fine-tuning, domain adaptation, or research into small-scale language model behavior. At 1.7 billion parameters, it provides meaningful language understanding and generation capabilities while remaining lightweight enough to train and experiment with on consumer hardware. Researchers and developers who want full control over downstream behavior will find this base model more flexible than the instruction-tuned version.

Qwen1.5 14B

Alibaba · 14.2B · runs from 8 GB

Qwen1.5-14B is Alibaba's base pretrained language model, not instruction-tuned, from the Qwen1.5 series that served as a beta preview of Qwen2. It is a dense Transformer with SwiGLU activations, QKV bias, and an improved multilingual tokenizer, released alongside a matching aligned chat model. The Qwen1.5 line spans eight sizes from 0.5B to 72B dense models plus a 14B-class Mixture-of-Experts model, all with stable 32K context support. At 14 billion parameters it fits comfortably on a single consumer GPU once quantized. Context length is 32,768 tokens. It is released under Alibaba's custom Tongyi Qianwen license, which permits commercial use below 100 million monthly active users. It was published in January 2024; Qwen1.5 has since been superseded by the Qwen2, Qwen2.5, and Qwen3 series.

Sarashina2.2 0.5B Instruct v0.1

sbintuitions · 793M · runs from 0.6 GB

Sarashina2.2 0.5B Instruct v0.1 is a 793M-parameter open language model from sbintuitions. 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.

GLM 4.1V 9B Thinking

Z.ai · 10.3B · runs from 4.8 GB

GLM 4.1V 9B Thinking is a 10.3-billion-parameter vision-language reasoning model jointly released by Z.ai (Zhipu AI) and Tsinghua University's KEG lab, built on the GLM-4-9B-0414 base. It is designed for multimodal chain-of-thought reasoning, working through long videos, image question answering, document interpretation, GUI-agent tasks, and code generation with an explicit "thinking" step before answering. At roughly 10B parameters, it runs on mainstream consumer GPUs once quantized, without needing workstation-class hardware. The model supports a 65K token context window and handles arbitrary aspect ratios up to 4K image resolution. It is released under the MIT license, one of the most permissive options available, allowing unrestricted commercial and research use. It was published in June 2025.

VisionReasoning

Internlm2 Chat 7B

InternLM · 7.7B · runs from 3.9 GB

Internlm2 Chat 7B is a 7.7B-parameter open language model from InternLM in the InternLM 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.

Gpt2 Xl

OpenAI · 1.6B · runs from 0.7 GB

GPT-2 XL is the largest variant of the GPT-2 family at 1.6 billion parameters, representing the full release of the model OpenAI originally withheld over safety concerns in 2019. It produces the most coherent and capable outputs of the GPT-2 lineup, though it remains far behind modern multi-billion-parameter instruction-tuned models. At its size, GPT-2 XL still runs easily on most consumer GPUs and even on CPUs with reasonable speed, making it useful for experimentation, fine-tuning projects, and as a baseline for comparing against newer architectures. It requires roughly 3 GB of VRAM at full precision.

Sqlcoder 7B 2

defog · 6.7B · runs from 4.2 GB

SQLCoder 7B 2 is a 6.7-billion-parameter model from Defog, purpose-built for converting natural-language questions into SQL queries. Fine-tuned specifically on text-to-SQL tasks, it consistently outperforms much larger general-purpose models when the job is generating accurate, executable SQL against real database schemas. For developers and data analysts who regularly query databases, running SQLCoder locally means fast, private SQL generation without sending proprietary schema details to an external API. It works best when provided with table definitions as context and is particularly strong on PostgreSQL, MySQL, and SQLite dialects.

Mistral Nemo Base 2407

Mistral AI · 12.2B · runs from 5.8 GB

Mistral-Nemo-Base-2407 is a 12-billion-parameter pretrained base language model jointly developed by Mistral AI and NVIDIA, intended as a drop-in replacement for the earlier Mistral 7B rather than a chat assistant; it has not been instruction-tuned or aligned, and the card notes it carries no built-in moderation mechanisms. It uses a standard transformer architecture with grouped-query attention and SwiGLU activations, and was trained on a large share of multilingual and code data across nine languages. At 12 billion parameters it fits comfortably on a single consumer GPU once quantized. Context length is 131,072 tokens (a 128k window). It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in July 2024, alongside an instruction-tuned Nemo variant.

InternVL2 1B

OpenGVLab · 938M · runs from 0.4 GB

InternVL2-1B is OpenGVLab's smallest instruction-tuned vision-language model in the InternVL 2.0 family, combining an InternViT-300M-448px vision encoder with a Qwen2-0.5B-Instruct language model via an MLP projector. It handles document and chart comprehension, OCR, scene-text reading, and general visual question answering, and can take multiple images or video frames as input. At under a billion parameters, it is light enough to run on a CPU or a low-end consumer GPU. InternVL 2.0 models were trained with an 8K context window and improved multi-image and video handling over the earlier InternVL 1.5 generation. Context length is 8,192 tokens. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in July 2024. It was later superseded by the InternVL2.5 series.

Pythia 1.4B

EleutherAI · 1.5B · runs from 0.7 GB

Pythia 1.4B is a 1.5B-parameter open language model from EleutherAI. 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.

Qwen1.5 14B Chat

Alibaba · 14.2B · runs from 8 GB

Qwen1.5 14B Chat is a 14.2B-parameter open language model from Alibaba in the Qwen 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.

GritLM 7B

GritLM · 7.2B · runs from 3.6 GB

GritLM 7B is a 7.2B-parameter open language model from GritLM. 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.

Qwen 14B Chat

Alibaba · 14.2B · runs from 6.6 GB

Qwen-14B-Chat is Alibaba Cloud's 14-billion-parameter bilingual Chinese/English chat model, aligned from the pretrained Qwen-14B base using supervised alignment techniques on top of large-scale web text, books, and code pretraining data. It supports tool and API use through ReAct-style prompting, the same pattern used by LangChain agents, and can extend beyond its native context via optional NTK-aware interpolation and LogN attention scaling for long-document summarization. At 14 billion parameters it fits a single consumer GPU once quantized. Context length is 8,192 tokens natively. It is released under the Tongyi Qianwen License Agreement, Alibaba's custom license that allows research and commercial use, with a separate application required for larger-scale commercial deployment. It was published in September 2023, part of the original Qwen generation that Alibaba has since superseded with Qwen1.5, Qwen2, and Qwen3.

Jina Ocr V1

jinaai · 3.4B · runs from 1.9 GB

jina-ocr-v1 is Jina AI's end-to-end document-parsing OCR model, built on the DeepSeek-OCR architecture. It combines a DeepEncoder vision tower, which represents a 1024x1024 page as just 256 visual tokens plus dynamic local tiles, with a 3-billion-parameter Mixture-of-Experts decoder, and adds a FastMTP speculative-decoding head that drafts several tokens at once to speed up long structured outputs. It reads documents into clean Markdown, converts equations to LaTeX and tables to HTML, and scores ahead of DeepSeek-OCR on the OmniDocBench and olmOCR-Bench document-parsing benchmarks. Its small active-parameter footprint lets it run on a single modest consumer GPU. Context length is 32,768 tokens. It is released under the CC BY-NC 4.0 license, which restricts use to non-commercial purposes. It was published in September 2026.

Tiny Starcoder Py

BigCode · 164M · runs from 0.1 GB

Tiny Starcoder Py is a 164M-parameter open language model from BigCode in the StarCoder 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.

Qwen2.5 Coder 1.5B

Alibaba · 1.5B · runs from 1.0 GB

Qwen2.5 Coder 1.5B is a 1.5-billion parameter code-specialized model from Alibaba Cloud's Qwen 2.5 Coder series. It is the smallest Coder variant that balances meaningful code generation capability with extremely low resource requirements, running on GPUs with as little as 2-4GB of VRAM. The model is suitable for lightweight code completion, simple code generation tasks, and as a compact local coding assistant in resource-constrained environments. It supports a 128K token context window. Released under the Apache 2.0 license.

SmolLM2 135M

Hugging Face · 135M · runs from 0.4 GB

SmolLM2 135M is one of the smallest capable language models available, developed by Hugging Face as part of their SmolLM2 family. With just 135 million parameters, it requires virtually no VRAM and can run on almost any hardware, making it an excellent starting point for researchers experimenting with language model behavior, fine-tuning workflows, or edge deployment scenarios. Despite its tiny footprint, SmolLM2 135M benefits from improved training data and techniques compared to its first-generation predecessor. It is best suited for lightweight text generation tasks, prototyping, and educational purposes rather than production-grade applications.

Llama 68M

JackFram · 68M · runs from 0.0 GB

Llama 68M is a 68M-parameter open language model from JackFram in the Llama family. 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.

Phi 1 5

Microsoft · 1.4B · runs from 0.7 GB

Phi 1 5 is a 1.4B-parameter open language model from Microsoft in the Phi family. 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.