Run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf locally

License: other ⬇ 546,362 ❤ 1
Parameters0.64B

handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf is a compact language model with 0.64 billion parameters, built on the parakeet architecture. It is released under the other license and has been downloaded 546,362 times.

To run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf locally at a 4,096-token context, its quantized versions need between 1.65 GB (Q4_K_M, lowest quality) and 3.56 GB (F32, highest quality) of memory, weights plus KV cache and a system margin included.

For most users the best balance is F32, needing about 3.56 GB. That means handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.

→ Guide: How much VRAM do you need?

All quantizations

Quant.Bits QualityWeights KVTotal Speed~Verdict
Q4_K_M 6.22 Very good 0.46 GB 0.39 GB 1.65 GB 866.2 t/s Fits in VRAM
Q5_K_M 7.02 Excellent 0.52 GB 0.39 GB 1.71 GB 767.4 t/s Fits in VRAM
Q6_K 7.79 Excellent 0.58 GB 0.39 GB 1.76 GB 691.2 t/s Fits in VRAM
Q8_0 9.42 Excellent 0.7 GB 0.39 GB 1.88 GB 571.8 t/s Fits in VRAM
F16 16.02 Excellent 1.19 GB 0.39 GB 2.38 GB 336.1 t/s Fits in VRAM
F32 32.0 Excellent 2.38 GB 0.39 GB 3.56 GB 168.3 t/s Fits in VRAM

KV cache estimated (architecture unavailable). Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

How much VRAM do you need to run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf?

You need about 3.56 GB of VRAM to run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf entirely on the GPU using the F32 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf on an 8 GB GPU?

Yes. With 8 GB of VRAM you can run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf fully on the GPU using F32 (about 3.56 GB).

Can I run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf fully on the GPU using F32 (about 3.56 GB).

Can I run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf fully on the GPU using F32 (about 3.56 GB).

What is the best quantization for handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf?

If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.