Update model card: add Q4_K to file table
Browse files
README.md
CHANGED
|
@@ -89,6 +89,7 @@ GGUF conversion of [nvidia/nemotron-3.5-asr-streaming-0.6b](https://huggingface.
|
|
| 89 |
| File | Size | Description |
|
| 90 |
|------|------|-------------|
|
| 91 |
| `nemotron-3.5-asr-streaming-0.6b-f16.gguf` | ~1.2 GB | F16 weights (full precision) |
|
|
|
|
| 92 |
| `nemotron-3.5-asr-streaming-ref.gguf` | ~1.2 GB | Reference GGUF (for parity testing) |
|
| 93 |
|
| 94 |
## Usage with CrispASR
|
|
|
|
| 89 |
| File | Size | Description |
|
| 90 |
|------|------|-------------|
|
| 91 |
| `nemotron-3.5-asr-streaming-0.6b-f16.gguf` | ~1.2 GB | F16 weights (full precision) |
|
| 92 |
+
| `nemotron-3.5-asr-streaming-0.6b-q4_k.gguf` | ~0.4 GB | Q4_K quantized (recommended) |
|
| 93 |
| `nemotron-3.5-asr-streaming-ref.gguf` | ~1.2 GB | Reference GGUF (for parity testing) |
|
| 94 |
|
| 95 |
## Usage with CrispASR
|