fix review findings and additional clean up#116
Open
iamleonie wants to merge 1 commit into
Open
Conversation
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
mlabonne
reviewed
Jul 11, 2026
| import { ChatMLExample } from "/snippets/key-concepts/chatml-example.mdx"; | ||
| import { ToolCallTokenExample } from "/snippets/key-concepts/tool-call-token-example.mdx"; | ||
|
|
||
| This guide is for teams already running Qwen, Llama, or Gemma who want to evaluate Liquid Foundation Models (LFMs) as replacements. LFMs load and serve through the same frameworks you already use, so most migrations are a model ID and configuration change. The details that usually matter are deployment runtime choice (see [Deployment runtimes](#deployment-runtimes)), chat templates (see [Chat Template](#chat-template)), sampling configuration (see [Sampling Configuration](#sampling-configuration)), tool-call parsing (see [Tool Use](#tool-use)), and LoRA module names (see [Fine-tuning](#fine-tuning)). |
Collaborator
There was a problem hiding this comment.
Could be split into two paragraphs or a bullet list
| | Qwen3 thinking mode or DeepSeek distills | [LFM2.5-1.2B-Thinking](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | Reasoning traces at 1.2B. | | ||
| | Qwen3-0.6B, Llama-3.2-1B, Gemma-3-270M/1B | [LFM2.5-230M](https://huggingface.co/LiquidAI/LFM2.5-230M) or [LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M) | Smallest text models for classification, extraction, routing, and tight memory budgets. | | ||
| | Qwen3-1.7B, Llama-3.2-3B, Gemma-3-4B, reasoning models in this latency class | [LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) or [LFM2.5-1.2B-Thinking](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | Choose the Thinking variant when reasoning quality is worth the added latency. | | ||
| | Qwen3-4B/8B, Llama-3.1-8B, Gemma-3-12B | [LFM2-2.6B](https://huggingface.co/LiquidAI/LFM2-2.6B) or [LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) | Compare in your latency and memory budget; 8B-A1B is an MoE model with 1.5B active parameters. | |
Collaborator
There was a problem hiding this comment.
Ok actually LFM2-2.6B is not something we should advertise because it's from the previous generation (the 8B-A1B will be better here), my bad!
| | Qwen3-4B/8B, Llama-3.1-8B, Gemma-3-12B | [LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) | MoE with 8B total and 1.5B active parameters. | | ||
| | Qwen3-14B/32B and larger dense models | [LFM2-24B-A2B](https://huggingface.co/LiquidAI/LFM2-24B-A2B) | 24B total and roughly 2.3B active parameters. | | ||
| | Qwen3 thinking mode or DeepSeek distills | [LFM2.5-1.2B-Thinking](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | Reasoning traces at 1.2B. | | ||
| | Qwen3-0.6B, Llama-3.2-1B, Gemma-3-270M/1B | [LFM2.5-230M](https://huggingface.co/LiquidAI/LFM2.5-230M) or [LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M) | Smallest text models for classification, extraction, routing, and tight memory budgets. | |
Collaborator
There was a problem hiding this comment.
I noticed that we're talking about Qwen3 and Gemma 3 instead of Qwen3.5 and Gemma 4 everywhere. We should probably either update it when there's a clear replacement or have both when there's none (particularly true for Gemma 4).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
lfm2parser and native Pythonic tool-call format. (confirmed its calledlfm2parser