---
license: other
license_name: lfm-open-license-v1.0
license_link: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/LICENSE
base_model: LiquidAI/LFM2.5-8B-A1B
tags:
- mlc-llm
- web-llm
- webgpu
- lfm2
- on-device
- mixture-of-experts
library_name: mlc-llm
pipeline_tag: text-generation
---

# LFM2.5-8B-A1B-q4f16_1-MLC

[LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) (Liquid AI), compiled to **MLC / WebGPU** (`q4f16_1`)
for in-tab / on-device inference via [WebLLM](https://github.com/mlc-ai/web-llm). Ported with
**[Kiln](https://github.com/NakliTechie/kiln)**, which adds the LFM2 hybrid architecture (LIV
short-conv + GQA/QK-norm + DeepSeek-V3-style MoE) to mlc-llm — notably **without any custom TVM operator**
(the conv-state rides an `RNNState` ring buffer alongside the KV cache).

- **Quantization:** `q4f16_1` (~4.44 GB) · **Context:** 4096 · **Decode:** ~93 tok/s on an M4 Pro (Metal).
- **Files:** `q4f16_1` weight shards + `mlc-chat-config.json` + tokenizer + `LFM2.5-8B-A1B-q4f16_1-webgpu.wasm` (WebGPU model lib).

## Use (WebLLM)

```js
import { CreateMLCEngine } from "@mlc-ai/web-llm";
const appConfig = { model_list: [{
  model: "https://huggingface.co/naklitechie/LFM2.5-8B-A1B-q4f16_1-MLC/resolve/main/",
  model_id: "LFM2.5-8B-A1B-q4f16_1-MLC",
  model_lib: "https://huggingface.co/naklitechie/LFM2.5-8B-A1B-q4f16_1-MLC/resolve/main/LFM2.5-8B-A1B-q4f16_1-webgpu.wasm",
  overrides: { context_window_size: 4096 },
}]};
const engine = await CreateMLCEngine("LFM2.5-8B-A1B-q4f16_1-MLC", { appConfig });
```

> ⚠️ **Runtime match.** Compiled with mlc-llm `main` (TVM 0.25.dev0); the cache manifest is
> `tensor-cache.json`. Load with a `@mlc-ai/web-llm` build whose bundled tvmjs matches — stock
> `0.2.84` expects an older runtime + `ndarray-cache.json` and will not load this as-is.

## Note — reasoning model

LFM2.5-8B-A1B emits `<think>…</think>` reasoning. At `q4` use **sampling + a repetition penalty**
(defaults are baked into `mlc-chat-config.json`: temp 0.7 / top_p 0.95 / frequency_penalty 0.5) —
greedy decoding degenerates into repetition (the unquantized original does too; this is model
behavior, not a port artifact — see Kiln `reference/gate-3-8b.md`).

## Attribution & license

Format conversion only. The original model and its **LFM Open License** are © Liquid AI
([LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B)). MLC compilation:
[Kiln](https://github.com/NakliTechie/kiln) · [NakliTechie/mlc-llm](https://github.com/NakliTechie/mlc-llm).