All LLM Models
Browse 31 LLM models with VRAM requirements, quantization options, and hardware compatibility.
Model List
Phi 4 Mini Instruct
Microsoft · 3.8B · runs from 4.8 GB at Q4
337.3K
886Microsoft Phi 4 Mini Instruct is a 3.8-billion parameter instruction-tuned model from Microsoft Research's Phi 4 family. It applies the Phi series' data-centric training philosophy to a compact model, delivering strong performance in coding, reasoning, and chat tasks relative to its small footprint. The model runs on consumer GPUs with as little as 4-6GB of VRAM when quantized, making it accessible on mainstream and even entry-level hardware. Released under the MIT license.
Phi 3.5 Mini Instruct
Microsoft · 3.8B · runs from 9.0 GB at Q4
Phi 3.5 Mini Instruct is a 3.8B-parameter open language model from Microsoft in the Phi 3 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.
Phi 4
Microsoft · 14.7B · runs from 12.5 GB at Q4
Microsoft Phi 4 is a 14-billion parameter language model from Microsoft Research's Phi series, designed to deliver strong reasoning, mathematical, and coding performance at an efficient size. Phi 4 continues the Phi family's focus on maximizing capability per parameter through high-quality training data curation, achieving benchmark scores that rival much larger models on reasoning and STEM tasks. The model runs well on consumer GPUs with 12-16GB of VRAM in quantized formats. It excels at mathematical problem solving, code generation, and structured reasoning. Released under the MIT license.
Phi 4 Mini Reasoning
Microsoft · 3.8B · runs from 4.8 GB at Q4
Phi-4-mini-reasoning is Microsoft's compact 3.8-billion-parameter model in the Phi-4 family, fine-tuned specifically for multi-step, logic-intensive mathematical reasoning using synthetic math data distilled from a larger teacher model. It targets tasks like formal proof generation, symbolic computation, and advanced word problems, and is designed to run in memory- and latency-constrained environments such as educational tools or embedded tutoring systems, rather than for general knowledge or open-domain chat. It supports a 128K token context window and is released under the MIT license. At 3.8 billion parameters, it runs comfortably on almost any modern laptop or consumer GPU, even at higher precision, making it one of the more accessible reasoning-focused models to run locally.
FrogNano 4B 2609
Microsoft · 4.7B · runs from 3.4 GB at Q4
FrogNano is Microsoft's compact repository-level coding agent, built from Qwen3.5-4B with around 4.7 billion parameters. It received post-training via reinforcement learning on roughly 1,500 synthetic software-engineering tasks using a lightweight five-tool harness named Leaf, and the card notes it avoids solution trajectories or reasoning traces from stronger models. The design retains the dense 32-layer hybrid Gated DeltaNet and gated-attention setup of its base. Intended for text-only work like repository navigation, debugging, code editing, test execution, and patch generation, this size means it runs on almost any modern GPU or many laptops, particularly when quantized. The model configuration supports 262,144 tokens, whereas the card describes an evaluated agent setup with about 131K tokens of combined context. The summary table in the card lists the Apache 2.0 license inherited from Qwen3.5-4B, while the repository is tagged MIT; both allow unrestricted commercial and research use. Released in September 2026, it serves as a specialist derivative of Qwen3.5-4B instead of a general-purpose chat model.
AesCode 8B
Microsoft · 8.8B · runs from 8.0 GB at Q4
AesCode-8B is the smaller of Microsoft's two AesCode models, which generate slides, posters, dashboards, and infographics as structured, editable HTML and CSS. It starts from Qwen3-VL-8B-Instruct and is trained with supervised fine-tuning and then reinforcement learning across seven reward channels. It can use an image generated from the same prompt as an aesthetic reference while taking the actual content from the text. On the paper's 300-sample infographic test, it scored 82.94 overall, a large gain over the 51.93 of its reference-conditioned base model. At about 8.8 billion parameters, it fits an 8 GB GPU at Q4 and runs well on 12 GB or more. The context window is 262,144 tokens, and the license is Apache 2.0. It accepts images and text. This is a design-to-code specialist rather than a general assistant, suited to producing editable visual documents locally. The larger AesCode-32B scores higher, reaching 85.89 overall.
AesCode 32B
Microsoft · 33.4B · runs from 23 GB at Q4
AesCode-32B is a Microsoft research model that writes slides, posters, dashboards, and infographics as editable HTML and CSS. It starts from Qwen3-VL-32B-Instruct and is trained with supervised fine-tuning followed by reinforcement learning on several reward signals. It can take an image generated from the same prompt as a style reference, which it uses for layout and look while taking the content from the text prompt. On the paper's 300-sample infographic test, it scored 85.89 overall, ahead of GPT-5.5 and Claude Opus 4.8 given the same reference. At about 33 billion parameters, a Q4 quant fits a 24 GB GPU. The context window is 262,144 tokens. It is released under the Apache 2.0 license. Because it is a vision-language model, it reads images as well as text. It is a specialist for design-to-code output rather than a general chat model, and the card pitches it for generating editable visual documents and for research on multimodal code generation. A smaller AesCode-8B sibling is also available.
Phi 2
Microsoft · 2.8B · runs from 2.6 GB at Q4
Microsoft Phi 2 is a 2.8-billion parameter language model from Microsoft Research that pioneered the concept of small but highly capable language models. Released in late 2023, Phi 2 demonstrated that strategic data curation and training methodology could allow a sub-3B model to outperform many 7B and 13B models on reasoning and coding benchmarks. The model runs on virtually any modern GPU and even on CPU-only setups. While succeeded by Phi 3 and Phi 4, Phi 2 remains historically significant as the model that proved small-scale language models could be genuinely useful for practical tasks. Released under the MIT license.
Phi 3 Mini 4k Instruct
Microsoft · 3.8B · runs from 4.2 GB at Q4
Microsoft Phi 3 Mini 4K Instruct is a 3.8-billion parameter instruction-tuned model from Microsoft Research's Phi 3 generation, with a 4K token context window. The Phi 3 family demonstrated that small models trained on carefully curated, high-quality data can achieve performance competitive with models several times their size. The model runs on consumer GPUs with as little as 4-6GB of VRAM when quantized, making it one of the most accessible capable chat models for local deployment. Released under the MIT license.
Phi 3 Medium 128k Instruct
Microsoft · 14.0B · runs from 12.0 GB at Q4
Phi-3-Medium-128K-Instruct is Microsoft's 14-billion-parameter instruction-tuned model in the Phi-3 family, trained on a mix of synthetic data and filtered high-quality web content chosen for reasoning density, then post-trained with supervised fine-tuning and direct preference optimization for instruction-following and safety. It is the long-context variant of Phi-3-Medium, alongside a 4K-context sibling, and is aimed at memory- and latency-constrained deployments needing strong code, math, and logical reasoning rather than frontier-scale serving. At 14B parameters, it runs on a single high-end consumer GPU once quantized. Context length is 131,072 tokens. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in May 2024.
Phi 3 Mini 128k Instruct
Microsoft · 3.8B · runs from 9.0 GB at Q4
Phi 3 Mini 128k Instruct is a 3.8B-parameter open language model from Microsoft in the Phi 3 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.
Phi 4 Reasoning Plus
Microsoft · 14.7B · runs from 12.5 GB at Q4
Phi 4 Reasoning Plus is a 14.7B-parameter open language model from Microsoft in the Phi 4 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.
Phi 4 Reasoning
Microsoft · 14.7B · runs from 12.5 GB at Q4
Phi-4-reasoning is Microsoft's reasoning-focused fine-tune of Phi-4, a 14-billion-parameter dense decoder-only transformer, produced through supervised fine-tuning on chain-of-thought traces followed by reinforcement learning, concentrated on math, science, and coding tasks plus safety alignment data. The fine-tuning set combined synthetic prompts with high-quality filtered public web data, and responses are structured in two parts: a reasoning trace followed by a final summarized answer. Microsoft designed it for memory- and compute-constrained, latency-bound scenarios rather than frontier-scale serving, and at 14B parameters it can run on a single high-end consumer GPU once quantized. Context length is 32,768 tokens. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in April 2025.
Phi 3.5 MoE Instruct
Microsoft · 41.9B · runs from 27.6 GB at Q4
Phi-3.5-MoE-instruct is Microsoft's Mixture-of-Experts model in the Phi-3.5 line, combining 16 experts of 3.8 billion parameters each, about 42 billion total, with only around 6.6 billion active per token. It is an instruction-tuned model refined with supervised fine-tuning, PPO, and DPO, built for multilingual reasoning tasks including code, math, and logic in memory- or latency-constrained deployments. It supports a 128K token context window and ships under the MIT license, allowing free commercial and research use. Because only about 6.6 billion parameters activate per token, it runs noticeably faster than its 42-billion-parameter size implies, though the full model still needs roughly 24 GB of memory at 4-bit quantization since all expert weights stay resident.
Phi Mini MoE Instruct
Microsoft · 7.6B · runs from 5.4 GB at Q4
Phi-mini-MoE-instruct is Microsoft's lightweight Mixture-of-Experts model featuring 7.6 billion total and 2.4 billion active parameters. According to the card, it was compressed and distilled from the base model used by Phi-3.5-MoE and GRIN-MoE via the SlimMoE approach, then post-trained with supervised fine-tuning and direct preference optimization for instruction following and safety. It targets English applications in memory- or compute-constrained environments where latency is a concern. Since only 2.4 billion parameters activate per token, it runs quickly, and its full weights fit on one consumer GPU after quantization. The context length reaches 4,096 tokens, which lags behind current standards. Released under the MIT license for both commercial and research use, it came out in June 2025. This model is part of the SlimMoE series, which also houses the smaller Phi-tiny-MoE with 3.8 billion total and 1.1 billion active parameters.
Phi 1 5
Microsoft · 1.4B · runs from 0.9 GB at Q4
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.
Phi Tiny MoE Instruct
Microsoft · 3.8B · runs from 3.1 GB at Q4
Phi Tiny MoE Instruct is a 3.8B-parameter open language model from Microsoft in the Phi 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 3.5 Vision Instruct
Microsoft · 4.1B · runs from 9.2 GB at Q4
Phi 3.5 Vision Instruct is Microsoft's 4.1-billion-parameter multimodal model, pairing an image encoder and connector with the Phi-3 Mini language model to handle text and code alongside pictures. It suits visual question answering, chart and table reading, document OCR, and comparing details across multiple images in one prompt. Its small size suits laptops and modest consumer GPUs, running smoothly even on limited hardware once quantized. The model supports a 128K token context window, enough for lengthy documents. It is released under the MIT license, one of the most permissive options available, allowing unrestricted commercial and research use. Published in August 2024, it was trained on roughly 500 billion tokens of synthetic and filtered web data.
DialoGPT Small
Microsoft · 176M · runs from 0.1 GB at Q4
DialoGPT Small is a 176M-parameter open language model from Microsoft. 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.
Phi 3 Vision 128k Instruct
Microsoft · 4.1B · runs from 4.9 GB at Q4
Phi 3 Vision 128k Instruct is a 4.1B-parameter open language model from Microsoft in the Phi 3 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.
Maira 2
Microsoft · 6.9B · runs from 7 GB at Q4
Maira 2 is a 6.9B-parameter open language model from Microsoft. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Bitnet B1.58 2B 4T
Microsoft · 850M · runs from 0.8 GB at Q4
Bitnet B1.58 2B 4T is a 850M-parameter open language model from Microsoft. 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 Medium 4k Instruct
Microsoft · 14.0B · runs from 9.5 GB at Q4
Phi 3 Medium 4k Instruct is a 14.0B-parameter open language model from Microsoft in the Phi 3 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 1
Microsoft · 1.4B · runs from 0.9 GB at Q4
Phi 1 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.
Phi 3 Small 8k Instruct
Microsoft · 7.4B · runs from 6.0 GB at Q4
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.
UserLM 8B
Microsoft · 8.0B · runs from 6.2 GB at Q4
UserLM 8B is a 8.0B-parameter open language model from Microsoft. 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.
MediPhi Instruct
Microsoft · 3.8B · runs from 9.0 GB at Q4
MediPhi Instruct is a 3.8B-parameter open language model from Microsoft in the Phi 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.
UserRepGen 4B
Microsoft · 4.5B · runs from 3.4 GB at Q4
UserRepGen 4B is a 4.5B-parameter open language model from Microsoft. 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.
Phi 4 Mini Flash Reasoning
Microsoft · 3.9B · runs from 5.3 GB at Q4
Phi 4 Mini Flash Reasoning is a 3.9B-parameter open language model from Microsoft in the Phi 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.
MAI DS R1
Microsoft · 671.0B · runs from 404.1 GB at Q4
MAI DS R1 is a 671.0B-parameter open language model from Microsoft. It supports a context window of up to 163,840 tokens. 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.