mms-1b-all
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve facebook/mms-1b-allNew 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
- Whisper Large V3 Turbo - 800M, 4,713,890 downloads/month
- distil-large-v3 - 760M, 745,014 downloads/month
- Qwen3-ASR-0.6B-hf - 780M, 532,640 downloads/month
- parakeet-tdt-0.6b-v3 - 630M, 531,382 downloads/month
- nemotron-3.5-asr-streaming-0.6b - 640M, 448,774 downloads/month
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