The Best Open Source Large Language Models Llms

The best open-source large language models (LLMs) Announcing our Series F . Learn more

AI models

The best open-source large language models (LLMs)

We compare 9 top open-source LLMs in production. Find the best model for agentic coding, long-context reasoning, cost, and speed.

Authors

Chloe Florit

Last updated June 17, 2026

Share

TL;DR We evaluated nine of the best open-source models: DeepSeek V4 Pro, Gemma 4, GLM-5.2, GPT OSS 120B, Kimi K2.7, MiniMax M3, Nemotron 3 Ultra, and Qwen 3.6. Kimi K2.7 is the most well-rounded; Qwen 3.6 and GLM-5.2 lead for agentic coding; DeepSeek and Nemotron dominate long-context and enterprise workloads; and GPT OSS 120B performs well on cost and speed.

New LLMs drop every day. With so many choices, it might be hard to select the right one! You might have a variety of tasks in front of you that could require coding, agentic workflows, or long context reasoning, for example. Whatever your use case is, we want to help you find the best open-source LLMs for it. In this blog, we’ll review the technical specifications, benchmarks, and first-hand data from models we currently run for customers in production at Baseten. DeepSeek V4 Pro DeepSeek V4 Pro is a frontier open-source model built for agentic coding and complex STEM reasoning. Its architecture allows for a 1M-token context window through a hybrid attention mechanism: CSA (Cross-layer Shared Attention) reuses the Key and Value matrices from the first layer across all subsequent layers. (Keys help the model figure out which words to pay attention to, and values determine what information gets added to a word's meaning based on which is relevant. They are collectively cached as the “KV cache”.) Key and Value matrices don’t change much between layers, so sharing them cuts memory significantly with only a minor quality tradeoff. HCA (Hierarchical Chunked Attention) splits the sequence into chunks: each token attends precisely to others in its own chunk, and coarsely to summaries of distant chunks. Close tokens get specific attention; far tokens get averaged context. Together, CSA and HCA reduce KV cache memory to roughly 2% of what standard models require. Manifold-Constrained Hyper-Connections (mHC) keep training stable at scale, allowing DeepSeek to reliably train models with massive context windows by replacing the standard residual addition between layers with a mathematically constrained mixing operation. What we love about DeepSeek V4 Pro: DeepSeek V4 Pro leads open-source models on agentic coding and matches closed-source frontier models

1M token context window to feed it an entire codebase or document library in a single call

CSA + HCA reduce KV cache memory to ~2% of standard transformer requirements which lowers inference costs and allows more requests to run on the same GPU

mHC keeps training stable at scale, enabling reliable performance across massive contexts

Significantly cheaper than comparable closed-source models on mid-to-high complexity tasks

You can try DeepSeek V4 Pro on Baseten. Gemma 4 Google DeepMind’s open-weight Gemma model is built for enterprise fine-tuning and multimodal reasoning. Gemma 4 alternates between sliding window attention, where each token only looks at a fixed window of neighboring tokens, and sparsely placed global attention layers, where every token attends to every other token in the full sequence. This cuts compute overhead sharply while preserving long-range reasoning. Context windows go up to 128K on edge deployments and 256K in the cloud. There are two notable Gemma 4 models: Gemma 4 12B is encoder-free, with native audio support. The model is best for local deployment and agentic workflows on consumer hardware.

Gemma 4 31B is a more capable dense model, better for high-quality outputs where hardware isn’t a constraint. It does not have native audio and uses more VRAM.

What we love about Gemma 4: Great for agentic apps and fine-tuning custom models

Interleaved local/global attention reduces memory and compute costs

Up to 256K context window in cloud deployments

Strong multimodal reasoning and agentic workflow performance

Try Gemma 4 on Baseten . GLM-5.2 GLM-5.2 from Zhipu AI (commonly called Z.ai) is built for long-horizon coding tasks that would require an agent to run for hours. It uses a Mixture of Experts (MoE) architecture with 256 experts, routing just 8 experts per token, so you get the reasoning capacity of a massive model at a lower compute cost. GLM’s sparse attention compresses all Key and Value matrices per layer into a single small latent matrix, reconstructing the full matrices on the fly. This reduces the KV cache size by roughly the number of attention heads. To reduce compute cost, GLM-5.2 added IndexShare. Layer 1 of the group runs the indexer and picks the top‑k token indices to attend to. Layers 2–4 reuse those same indices instead of recomputing them across every transformer layer. GLM-5.2 actively manages its own working memory rather than just accumulating context, letting it iterate and self-correct through runs spanning hours to tens of hours. What we love about GLM-5.2: Stronger multi-hour agentic coding workflows than GLM 5.1

Dynamic working memory enables up to tens of hours of autonomous execution without context overload, making it well-suited for coding agents

1M context window via sparse attention and IndexShare

Experiment with GLM-5.2 on Baseten. GPT OSS 120B OpenAI's open-weight reasoning model, GPT OSS, is optimized for text generation and conversational AI. It’s cost-efficient and hits 650+ tokens/second on Baseten with NVIDIA GPUs, making it one of the fastest and most affordable 120B models available. Baseten reached 650+ TPS on GPT OSS 120B by using TensorRT-LLM on B200 GPUs and NVIDIA Dynamo (for KV cache-aware routing) at launch, then added EAGLE-3 speculative decoding , which uses a smaller ~1B draft model to predict tokens in parallel and delivers a 60% speed boost. What we love about GPT OSS 120B: 650+ tokens/second on Baseten; one of the fastest 120B models available

Optimized for consumer hardware (~80GB), making deployment straightforward

One of the cheapest 120B models to run without sacrificing generation quality

You can deploy GPT OSS 120B on Baseten. Kimi K2.6 Moonshot AI's 1-trillion-parameter model is highly reliable for coding workloads. Built around the Kimi Code engine , it can handle large codebases and build interfaces directly from visual mockups. Kimi...