mlboydaisuke / LFM2.5-350M-ExecuTorch

huggingface.co
Total runs: 82
24-hour runs: 0
7-day runs: -4
30-day runs: -172
Model's Last Updated: September 04 2026
text-generation

Introduction of LFM2.5-350M-ExecuTorch

Model Details of LFM2.5-350M-ExecuTorch

LFM2.5-350M — ExecuTorch XNNPACK 8da4w

lfm2_5_350m_xnnpack_8da4w.pte (252.8 MB)

  • Source : LiquidAI/LFM2.5-350M (hybrid conv/attention, 16 layers)
  • License : LFM Open License v1.0
  • Quantization : 8da4w (8-bit dynamic activation / 4-bit weight) + 8-bit embedding ( embedding_quantize: "8,0" )
  • Export : executorch 1.4.0 export_llm , dynamic shape, max_seq_length 2048, XNNPACK extended_ops
  • Config : llm_params/lfm2_5_350m_xnnpack_8da4w.yaml
Verification (Mac arm64, 2026-08-13)

Generation gate 3/3 via examples/models/llama/runner/native.py (greedy):

prompt output
capital of France? "The capital of France is Paris."
日本の首都は?(日本語) 「日本の首都は東京です。」
haiku about autumn leaves 3-line poem, coherent

Known cosmetic warning: params vocab_size (65536) != tokenizer vocab size.

iPhone 17 Pro (ETBench, XNNPACK CPU, default threads, 2026-08-13)
metric value
load 0.5 s
ttft (short prompt) 0.03 s
decode 171-173 tok/s

Outputs correct (Paris; coherent 128-token story).

Usage note — chat template is required. This is an instruct model: raw untemplated text makes it emit <|im_end|> immediately (looks like broken generation but is not). Always wrap prompts as <|startoftext|><|im_start|>user\n...<|im_end|>\n<|im_start|>assistant\n , eos ids [7].

Runs of mlboydaisuke LFM2.5-350M-ExecuTorch on huggingface.co

82
Total runs
0
24-hour runs
-5
3-day runs
-4
7-day runs
-172
30-day runs

More Information About LFM2.5-350M-ExecuTorch huggingface.co Model

More LFM2.5-350M-ExecuTorch license Visit here:

https://choosealicense.com/licenses/other

LFM2.5-350M-ExecuTorch huggingface.co

LFM2.5-350M-ExecuTorch huggingface.co is an AI model on huggingface.co that provides LFM2.5-350M-ExecuTorch's model effect (), which can be used instantly with this mlboydaisuke LFM2.5-350M-ExecuTorch model. huggingface.co supports a free trial of the LFM2.5-350M-ExecuTorch model, and also provides paid use of the LFM2.5-350M-ExecuTorch. Support call LFM2.5-350M-ExecuTorch model through api, including Node.js, Python, http.

LFM2.5-350M-ExecuTorch huggingface.co Url

https://huggingface.co/mlboydaisuke/LFM2.5-350M-ExecuTorch

mlboydaisuke LFM2.5-350M-ExecuTorch online free

LFM2.5-350M-ExecuTorch huggingface.co is an online trial and call api platform, which integrates LFM2.5-350M-ExecuTorch's modeling effects, including api services, and provides a free online trial of LFM2.5-350M-ExecuTorch, you can try LFM2.5-350M-ExecuTorch online for free by clicking the link below.

mlboydaisuke LFM2.5-350M-ExecuTorch online free url in huggingface.co:

https://huggingface.co/mlboydaisuke/LFM2.5-350M-ExecuTorch

LFM2.5-350M-ExecuTorch install

LFM2.5-350M-ExecuTorch is an open source model from GitHub that offers a free installation service, and any user can find LFM2.5-350M-ExecuTorch on GitHub to install. At the same time, huggingface.co provides the effect of LFM2.5-350M-ExecuTorch install, users can directly use LFM2.5-350M-ExecuTorch installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

LFM2.5-350M-ExecuTorch install url in huggingface.co:

https://huggingface.co/mlboydaisuke/LFM2.5-350M-ExecuTorch

Url of LFM2.5-350M-ExecuTorch

LFM2.5-350M-ExecuTorch huggingface.co Url

Provider of LFM2.5-350M-ExecuTorch huggingface.co

mlboydaisuke
ORGANIZATIONS

Other API from mlboydaisuke