All LLM Models
Browse 126 LLM models with VRAM requirements, quantization options, and hardware compatibility.
Model List
Qwen3 VL 8B Thinking
Alibaba · 8.8B · runs from 8.0 GB at Q4
128.8K
234Qwen3 VL 8B Thinking is an 8.8-billion-parameter vision-language model from Alibaba's Qwen team, the reasoning-focused counterpart to the Qwen3-VL-8B Instruct model. It processes images, video, and text together and is tuned to work through problems step by step before answering, which tends to help on multi-step visual reasoning, STEM problems, and chart or document analysis. At under 9 billion parameters, it runs well on a single mainstream consumer GPU once quantized, making local multimodal use practical without server-class hardware. It supports a 262K token context window for long documents, multi-image input, or extended video. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in October 2025 alongside the non-thinking Instruct variant, it trades some response speed for deeper visual-language reasoning.
Qwen2.5 Coder 1.5B
Alibaba · 1.5B · runs from 1.7 GB at Q4
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.
Qwen3 VL 4B Thinking
Alibaba · 4.4B · runs from 4.5 GB at Q4
Qwen3 VL 4B Thinking is Alibaba's 4.4-billion-parameter vision-language model within the Qwen3-VL lineup: a reasoning-focused edition that processes images and text before responding. The card emphasizes visual agent skills for controlling PC and mobile GUIs, coding directly from images and video, improved spatial awareness, and OCR support covering 32 languages. At this scale, it runs smoothly on one modest consumer GPU after quantization. The model handles a 262,144 token context window; the card notes this is native at 256K and expandable up to 1M. Released under the Apache 2.0 license, it allows unrestricted commercial and research use. Published in October 2025, it comes alongside an Instruct variant of identical size and introduces Interleaved-MRoPE, DeepStack, and text-timestamp alignment to enhance video understanding.
Qwen3.5 0.8B Base
Alibaba · 873M · runs from 0.9 GB at Q4
Qwen3.5-0.8B-Base is Alibaba's smallest base checkpoint in the Qwen3.5 family, at 0.87 billion parameters, a native vision-language foundation model that fuses image and text tokens during pretraining rather than bolting a vision encoder onto a text-only model. Like the rest of the -Base line, it ships as pretrained-only weights for fine-tuning and research, not direct interaction, though its control tokens support efficient LoRA-style adaptation with the official chat template. Its hybrid architecture pairs Gated DeltaNet linear attention with periodic full attention layers. It runs easily on a single modest consumer GPU, even unquantized. Context length is 262,144 tokens natively, extensible up to 1,010,000 tokens. It is released under the Apache 2.0 license, and was published in February 2026 as the smallest of five Qwen3.5-Base sizes, from 0.8B dense up to a 35B mixture-of-experts model.
Qwen3 VL 2B Thinking
Alibaba · 2.1B · runs from 3.5 GB at Q4
Qwen3-VL-2B-Thinking is Alibaba's 2.1-billion-parameter vision-language model, the reasoning-enhanced "Thinking" edition of the smallest Qwen3-VL checkpoint, alongside a matching Instruct edition. Beyond image description and visual question answering, it acts as a visual agent capable of operating PC and mobile GUIs, generating code from screenshots or diagrams, and reasoning about 2D and 3D spatial relationships. Its OCR pipeline covers 32 languages and is tuned for low light, blur, and tilted text. At just over 2 billion parameters, it runs easily on a single modest consumer GPU, even unquantized. The model natively supports a 262,144 token context window, expandable to 1,010,000 tokens for long documents or hours of video. It is released under the Apache 2.0 license, and was published in October 2025. Compared with Qwen2.5-VL, Qwen3-VL adds DeepStack vision-feature fusion and timestamp-grounded video event localization.
Qwen2 0.5B Instruct
Alibaba · 494M · runs from 0.8 GB at Q4
Qwen2 0.5B Instruct is a 494M-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.
Qwen2.5 Coder 3B
Alibaba · 3.1B · runs from 2.8 GB at Q4
Qwen2.5-Coder-3B is Alibaba's 3.1-billion-parameter base (pretrained, not instruction-tuned) code language model, one of six sizes in the Qwen2.5-Coder family built on Qwen2.5-3B. It was pretrained on 5.5 trillion tokens of source code, text-code grounding data, and synthetic data, and is intended as a foundation for further fine-tuning, reinforcement learning, or fill-in-the-middle code-completion tasks rather than direct chat use; Alibaba explicitly advises against using it for conversations as-is. The family's larger 32B model is described as matching GPT-4o-level coding ability, though this 3B checkpoint targets lightweight, resource-constrained deployment. At just over 3 billion parameters, it runs easily on a single modest consumer GPU or even a CPU. Context length is 32,768 tokens. It is released under the Qwen Research License, a non-commercial license restricted to research and evaluation use; commercial use requires a separate license from Alibaba Cloud. It was published in November 2024.
Qwen3 0.6B Base
Alibaba · 596M · runs from 1.6 GB at Q4
Qwen3 0.6B Base is the smallest pretrained foundation model in Alibaba Cloud's Qwen 3 family, with approximately 600 million parameters. As a base model, it is not tuned for chat or instructions and is intended for fine-tuning, research, and experimentation. Its minimal size makes it suitable for rapid prototyping and resource-constrained training experiments. The model runs on virtually any hardware, including CPU-only setups. It is useful for educational purposes, architecture exploration, and as a compact foundation for task-specific fine-tuning where model size is a primary constraint. Released under the Apache 2.0 license.
Qwen2.5 Coder 32B
Alibaba · 32.8B · runs from 24.3 GB at Q4
Qwen2.5-Coder-32B is Alibaba's 32.8-billion-parameter code-specialized base language model, the largest of six sizes in the Qwen2.5-Coder family (0.5B to 32B), continued-pretrained from Qwen2.5-32B on 5.5 trillion tokens of source code, text-code grounding data, and synthetic data. It is a raw pretrained model, not instruction-tuned, so it is meant as a foundation for building code assistants, agents, or chat models through further fine-tuning rather than for direct conversational use. Alibaba states its coding ability rivals GPT-4o, and at this size it needs a high-end consumer GPU or multi-GPU setup once quantized, more at full precision. Context length defaults to 32,768 tokens, extendable to 131,072 tokens with YaRN scaling. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in November 2024.
Qwen3.5 2B Base
Alibaba · 2.3B · runs from 1.9 GB at Q4
Qwen3.5-2B-Base is a 2.3-billion-parameter dense checkpoint in Alibaba's Qwen3.5 base model family, a native vision-language foundation model rather than a text-only model with vision bolted on. It is pretrain-only: fine-tuning, in-context-learning, or further research, not direct conversation, though its control tokens are compatible with the official chat template for efficient LoRA-style adaptation. Its hybrid architecture pairs Gated DeltaNet linear attention with periodic gated full-attention layers. At 2.3B parameters, it runs comfortably on a single consumer GPU, even unquantized. The model supports a native 262,144 token context window, extensible up to 1,010,000 tokens. It is released under the Apache 2.0 license, and was published in February 2026. Qwen3.5 introduced early-fusion multimodal pretraining that Alibaba says outperforms the separate Qwen3-VL models on reasoning, coding, and visual understanding.
Qwen2.5 3B
Alibaba · 3.1B · runs from 2.8 GB at Q4
Qwen2.5 3B is a 3.1B-parameter open language model from Alibaba 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.
Qwen2.5 14B Instruct 1M
Alibaba · 14.8B · runs from 12.4 GB at Q4
Qwen2.5 14B Instruct 1M is a 14.8B-parameter open language model from Alibaba in the Qwen 2.5 family. It supports a context window of up to 1,010,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3 14B Base
Alibaba · 14.8B · runs from 11.8 GB at Q4
Qwen3 14B Base is a 14.8B-parameter open language model from Alibaba in the Qwen 3 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.
Qwen2.5 Coder 14B
Alibaba · 14.8B · runs from 12.4 GB at Q4
Qwen2.5 Coder 14B is a 14.8B-parameter open language model from Alibaba 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 35B A3B Base
Alibaba · 36.0B · runs from 22.0 GB at Q4
Qwen3.5-35B-A3B-Base is the mixture-of-experts member of Alibaba's Qwen3.5 base family, pairing a 256-expert MoE layer (8 routed plus 1 shared expert per token) with the same Gated DeltaNet and gated-attention hybrid backbone used across the line. It totals roughly 36 billion parameters but activates only about 3 billion per token (the "A3B" in its name), so decoding stays fast even though the full expert set must stay resident in memory. Like its dense siblings it is pretrain-only, for fine-tuning and research, not direct chat; unlike them, its card lists only a pretraining stage, with no post-training pass. It needs a high-end consumer GPU once quantized. Context length is 262,144 tokens natively, extensible to 1,010,000 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in February 2026, alongside four smaller dense Qwen3.5-Base models from 0.8B to 9B parameters.
Qwen2 1.5B Instruct
Alibaba · 1.5B · runs from 1.7 GB at Q4
Qwen2 1.5B Instruct is a 1.5B-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.
Qwen2.5 Coder 7B
Alibaba · 7.6B · runs from 5.8 GB at Q4
Qwen2.5 Coder 7B is a 7.6-billion parameter code-specialized base (pretrained) model from Alibaba Cloud's Qwen 2.5 Coder series. It is trained on a large dataset of source code and natural language but is not instruction-tuned, making it suitable for fine-tuning, code-related research, and custom downstream applications. The model supports a 128K token context window and runs efficiently on consumer GPUs. It serves as the foundation for the Qwen2.5 Coder 7B Instruct variant and community fine-tunes targeting specific programming languages or workflows. Released under the Apache 2.0 license.
Qwen3 8B Base
Alibaba · 8.2B · runs from 7.6 GB at Q4
Qwen3 8B Base is an 8.2-billion parameter pretrained foundation model from Alibaba Cloud's Qwen 3 series. As a base model, it is not instruction-tuned and is intended for fine-tuning, research, and as a starting point for custom downstream applications. It was trained on a large multilingual corpus with improved data quality and training methodology compared to the Qwen 2.5 generation. The model runs efficiently on consumer GPUs with 8GB or more of VRAM and serves as the foundation for the Qwen3 8B instruction-tuned variant and community fine-tunes. It is a strong choice for practitioners building specialized models through further training. Released under the Apache 2.0 license.
Qwen2.5 72B
Alibaba · 72.7B · runs from 49.3 GB at Q4
Qwen2.5-72B is the base, pretrained 72.7-billion-parameter language model from Alibaba's Qwen2.5 series — it is not instruction-tuned and is not intended for direct conversational use; Alibaba recommends applying SFT, RLHF, or further pretraining on top of it. It uses a Transformer architecture with RoPE, SwiGLU, RMSNorm, QKV attention bias, 80 layers, and grouped-query attention (64 query heads, 8 key/value heads), with stronger coding, math, and structured-output ability than the earlier Qwen2 line, plus multilingual coverage across 29-plus languages. At 72.7 billion parameters, it needs a multi-GPU workstation to run at full precision, though quantized versions fit fewer cards. Context length is 131,072 tokens. It is released under Alibaba's custom Qwen license, which permits research and commercial use but requires a separate license from Alibaba once a product or service passes 100 million monthly active users. It was published in September 2024.
Qwen3 1.7B Base
Alibaba · 1.7B · runs from 3.2 GB at Q4
Qwen3 1.7B Base is a 1.7-billion parameter pretrained foundation model from Alibaba Cloud's Qwen 3 family. It is a compact base model designed for fine-tuning, research, and custom applications rather than direct conversational use. Its small size makes it accessible for resource-constrained fine-tuning and rapid experimentation. The model can run on virtually any modern GPU and benefits from the improved pretraining data of the Qwen 3 generation. It is suitable as a lightweight foundation for domain-specific fine-tunes and student models in distillation pipelines. Released under the Apache 2.0 license.
Qwen3 4B Base
Alibaba · 4.0B · runs from 4.2 GB at Q4
Qwen3-4B-Base is Alibaba's 4-billion-parameter base pretrained model from the Qwen3 generation, the successor to Qwen2.5. Like other -Base checkpoints, it is a raw causal language model meant for fine-tuning or research, not direct conversation. Qwen3 was trained on 36 trillion tokens across 119 languages, tripling Qwen2.5's language coverage, using a three-stage pipeline that builds general knowledge, then reasoning skills in code and STEM, then extends context length. At 4B dense parameters, it runs easily on a single consumer GPU, even without heavy quantization. The model supports a 32,768 token context window. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in April 2025. Qwen3 introduced a mix of dense and mixture-of-experts models alongside refinements like QK layernorm for training stability.
Qwen2 VL 72B Instruct
Alibaba · 73.4B · runs from 49.7 GB at Q4
Qwen2-VL-72B-Instruct is Alibaba's 73-billion-parameter instruction-tuned vision-language model, built by fine-tuning Qwen2-VL-72B. The card shows state-of-the-art results on benchmarks such as MathVista, DocVQA, RealWorldQA and MTVQA; it handles videos over 20 minutes long, recognizes multilingual text within images, and acts as an agent to control phones or robots. It added naive dynamic resolution, mapping images of any size to a variable number of visual tokens. A model this large requires multi-GPU setups or big unified-memory machines even when quantized. The context window holds 32,768 tokens. Released under the Tongyi Qianwen license instead of Apache 2.0, you should review its terms before commercial use. Published in September 2024, it has since been superseded by Qwen2.5-VL-72B-Instruct, which the card lists as the newer version.
Qwen2 7B
Alibaba · 7.6B · runs from 5.8 GB at Q4
Qwen2 7B is a 7.6B-parameter open language model from Alibaba in the Qwen 2 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.
QwQ 32B Preview
Alibaba · 32.8B · runs from 24.3 GB at Q4
QwQ 32B Preview is a 32.8B-parameter open language model from Alibaba in the QwQ 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.
Qwen2.5 1.5B
Alibaba · 1.5B · runs from 1.7 GB at Q4
Qwen2.5-1.5B is Alibaba's 1.5-billion-parameter entry in the Qwen2.5 family, released as a base pretrained language model rather than an instruction-tuned chat model. Qwen2.5 improved knowledge, coding, and math capabilities over its predecessor through an expanded pretraining corpus, but this checkpoint is the raw base: the model card explicitly discourages using it directly for conversation and recommends fine-tuning (SFT, RLHF, or continued pretraining) first. At this size, it runs comfortably on almost any modern GPU, or even a CPU, without quantization. The model supports a 131,072 token context window and is released under the Apache 2.0 license, allowing unrestricted commercial and research use. It was published in September 2024 alongside the rest of the Qwen2.5 line, which spans from 0.5B to 72B parameters and adds multilingual support for over 29 languages.
Qwen3.5 4B Base
Alibaba · 4.7B · runs from 3.4 GB at Q4
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.
Qwen2.5 7B
Alibaba · 7.6B · runs from 5.8 GB at Q4
Qwen2.5-7B is Alibaba's 7.6-billion-parameter base pretrained model in the Qwen2.5 series, one step up from the 1.5B checkpoint. Like its smaller sibling it is a raw causal language model rather than an instruction-tuned chat model: the card recommends applying supervised fine-tuning, RLHF, or further pretraining before using it conversationally. It uses a dense transformer with grouped-query attention, and at 7.6B parameters it fits comfortably on a single consumer GPU once quantized, or unquantized on a higher-memory card. Context length is 131,072 tokens, one of the longer windows in the 0.5B-to-72B Qwen2.5 lineup. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in September 2024. Qwen2.5 as a whole brought major gains in coding, math, and structured-data understanding over Qwen2.
Qwen2.5 0.5B
Alibaba · 494M · runs from 0.8 GB at Q4
Qwen2.5 0.5B is the smallest base (pretrained) model in Alibaba Cloud's Qwen 2.5 family, with 494 million parameters. As a base model, it is not instruction-tuned and is intended for fine-tuning, research, and as a foundation for custom applications. It supports a 128K token context window. Its minimal size makes it suitable for experimentation, rapid prototyping, and resource-constrained fine-tuning tasks. The model can run on virtually any hardware. Released under the Apache 2.0 license.
Qwen1.5 110B Chat
Alibaba · 111.2B · runs from 72.4 GB at Q4
Qwen1.5-110B-Chat is Alibaba Cloud's 111-billion-parameter dense chat model and the largest member of the Qwen1.5 series, which the team describes as a beta version of Qwen2 spanning nine sizes from 0.5B up to this 110B model plus a 14B mixture-of-experts variant. Unlike most other Qwen1.5 sizes, the 110B model uses grouped-query attention, and it was post-trained with supervised fine-tuning and direct preference optimization for improved chat alignment. At 111 billion parameters it needs a multi-GPU workstation to run even when quantized. Context length is 32,768 tokens, one of Qwen1.5's standout features since every size in the family shares a stable 32K window. It is released under the Tongyi Qianwen License Agreement, Alibaba's custom license permitting research and commercial use. It was published in April 2024, a beta step between the original Qwen and Qwen2.
Qwen2 72B Instruct
Alibaba · 72.7B · runs from 49.3 GB at Q4
Qwen2-72B-Instruct is the instruction-tuned, chat-ready 72.7-billion-parameter model from Alibaba's Qwen2 series, built on a Transformer architecture with SwiGLU activation, QKV attention bias, and grouped-query attention, and trained with supervised fine-tuning plus direct preference optimization. It generally surpassed the prior Qwen1.5 line and competed with proprietary models on language understanding, generation, multilingual tasks, coding, and math benchmarks at release, though it has since been superseded by Qwen2.5-72B-Instruct. At 72.7 billion parameters, it needs a multi-GPU workstation to run in full precision. Context length is natively 32,768 tokens, extendable to 131,072 tokens using YaRN scaling, as documented on the model card. It is released under Alibaba's Tongyi Qianwen custom license, which permits commercial use but requires a separate license once a deployment passes 100 million monthly active users. It was published in May 2024.
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.