mms-1b-all
facebookcc-by-nc-4.0audio

mms-1b-all

Updated Nov 21, 2026
Parameters
960M
License
cc-by-nc-4.0
Updated
Nov 21, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit mms-1b-all with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
2 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve facebook/mms-1b-all

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

mms-1b-all is an open-weight speech recognition model published by facebook on Hugging Face in May 2023, with 960M parameters under the cc-by-nc-4.0 license.

Among the 25 speech recognition models in this directory it ranks 17th by monthly Hugging Face downloads, and 7 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 2 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.

Similar speech recognition modelsLink to this section

PopularityLink to this section

mms-1b-all was downloaded 234,617 times on Hugging Face in the last month (11,437,683 all-time) and has 221 likes.

Run it locallyLink to this section

Weights and usage instructions are on the facebook/mms-1b-all model card; it loads with Hugging Face Transformers.

Local runtimes that fit this model:

  • transformers - the reference Python library most model cards target

PaperLink to this section

Frequently asked

Quick answers to common questions

How much VRAM does mms-1b-all need?

mms-1b-all with 960M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is mms-1b-all better than other facebook models?

mms-1b-all has 960M parameters - a strong choice for speech-recognition.

What license is mms-1b-all under?

mms-1b-all is released under the cc-by-nc-4.0 license, making it suitable for most commercial and personal projects.

What hardware runs mms-1b-all well?

With 960M parameters, mms-1b-all is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.

What is the best quantization for mms-1b-all?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with mms-1b-all?

mms-1b-all competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec