Run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF locally
rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF is a compact instruction-tuned chat model with 1.81 billion parameters, built on the llama architecture. It is released under the other license and has been downloaded 918,573 times.
To run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF locally at a 4,096-token context, its quantized versions need between 2.23 GB (Q4_K_M, lowest quality) and 2.23 GB (Q4_K_M, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is Q4_K_M, needing about 2.23 GB. That means rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q4_K_M | 5.01 | Very good | 1.06 GB | 0.38 GB | 2.23 GB | 378.8 t/s | Fits in VRAM |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF?
You need about 2.23 GB of VRAM to run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF entirely on the GPU using the Q4_K_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF fully on the GPU using Q4_K_M (about 2.23 GB).
Can I run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF fully on the GPU using Q4_K_M (about 2.23 GB).
Can I run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF fully on the GPU using Q4_K_M (about 2.23 GB).
What is the best quantization for rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-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.