Model Catalog

Don't have LM Studio yet? Get it formacOS,Windows, orLinux.

Hermes 3 Llama 3.2 3B

NousResearch

llama

3b

A generalist model with agentic capabilities, improved roleplaying, reasoning, multi-turn conversation, long context coherence

Llama 3.3 70B Instruct

lmstudio-community

llama

70B

Meta's latest Llama 70B model, matches the performance of Llama 3.2 405B

Qwen2.5 Coder 14B

Alibaba

qwen

14B

14B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

Qwen2.5 Coder 32B

Alibaba

qwen

32B

32B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

Qwen2.5 Coder 3B

Alibaba

qwen

3B

3B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

Llama 3.2 1B

Meta

llama

1B

A tiny and speedy Llama model from Meta, optimized for multilingual dialogue use cases.

Llama 3.2 3B

Meta

llama

3B

The new and small Llama model from Meta, optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

Qwen2.5 Coder 7B

Alibaba

qwen

7B

Code-specific LLMs for code generation, code reasoning and code fixing, supporting context length of up to 128K.

Qwen2.5 14B

Qwen

qwen

14B

An LLM specializing in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating JSON structured outputs.

Yi Coder 9B

01-ai

llama

9B

Yi Coder is a Llama fine-tune with expanded size, trained for code. Supports max 128K tokens and "52 major programming languages".

Hermes 3 Llama 3.1 8B

NousResearch

llama

8B

A fine-tune of Meta's Llama 3.1, Hermes is further trained on hand-curated datasets as well and synthetic data. Excels in dialogue and code generation.

InternLM 2.5 20B

InternLM

internlm2

20B

InternLM 2.5 offers strong reasoning across the board as well as tool use for developers, while sitting at the sweet spot of size for those with 24GB GPUs.

LLaVA v1.5

Haotian et al

llava

7B

The original LLaVA vision-enabled model, supporting image input and textual instruction following.

Meta Llama 3.1 8B

Meta

llama

8B

The latest in Meta's long-running Llama series, Llama 3.1 is another jack of all trades and master of some, now in 8 languages and up to 128k tokens.

Mistral Nemo 2407

MistralAI

mistral

12B

A slightly larger 12B parameter model from Mistral AI, NeMo offers a long 128k token context length, advanced world knowledge, and function calling for developers.

Gemma 2 2B

Google

gemma2

2B

"Google's Llama", Gemma benefits from Google's experience training its flagship Gemini model to provide excellent performance on low power or for autocompletion/drafting tasks.

Mathstral 7B

MistralAI

mistral

7B

A scientific specialist finetune of Mistral AI's popular 7B model, Mathstral excels at STEM chats and tasks.

Gemma 2 9B

google

gemma

9B

The mid-sized option of the Gemma 2 model family. Built by Google, using from the same research and technology used to create the Gemini models

SmolLM 360M v0.2

HuggingFace

llama

360M

A HuggingFace original model, SmolLM lives up to its name in size and will fit on just about any device. Slightly larger option at 1.7B parameters is also available.

Gemma 2 27B

google

gemma

27B

The large option of the Gemma 2 model family. Built by Google, using from the same research and technology used to create the Gemini models

Codestral 22B

MistralAI

mistral

22B

Mistral AI's latest coding model, Codestral can handle both instructions and code completions with ease in over 80 programming languages.

Phi 3.1 Mini 128k

Microsoft

phi3

3.8B

Microsoft's latest Phi Mini model supports a whopping context length of 128k tokens in a small size, offering extremely long chats for cheap.

DeepSeek Coder V2 Lite

DeepSeek

deepseek2

15.7B

The younger sibling of the GPT-4-beating 236B Deepseek Coder V2 model, this model also comes out strong with support for 338 different languages!

Qwen2 Math 1.5B

Alibaba

qwen

1.5B

A small model from Alibaba's Qwen2 family that punches above its weight in mathematical and multi-step logical reasoning.

Qwen 2 0.5B

Qwen

qwen2

0.5B

Promising 27 languages and lightning fast responses, this is the smallest entry in Alibaba's Qwen2 family that scales up to 72B parameters.

Aya 23 8B

C4AI

command-r

8B

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities.

Mistral 7B v0.3

MistralAI

mistral

7B

One of the most popular open-source LLMs, Mistral's 7B Instruct model's balance of speed, size, and performance makes it a great general-purpose daily driver.

StableCode

Stability AI

stablelm

2.7B

From the team behind Stable Diffusion, this small code model offers an excellent coding assistant for those with lighter hardware.

Command-R

CohereForAI

cohere

35B

Able to chat in more than 10 languages, Cohere AI's Command-R is optimized for RAG but can perform well in any task.

StarCoder2 7B

BigCode

starcoder2

7B

Also coming in 3B, 15B, and Chat versions, the StarCoder2 family offers a diverse portfolio of local coding assistants.

DeepSeek Math 7B

DeepSeek

deepseek

7B

Promising comparable performance to GPT-4 on mathematical reasoning, DeepSeek Math also offers the ability to write code to solve and prove mathematical problems.

lmmy