Gigax NPC LLM 3 8B needs about 0.6 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.1 GB (Q4_K_M) to 2.4 GB (Q4_K).
Gigax NPC LLM 3 8B is a 3.82B-parameter Gigax model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 14 quant files, from 0.1 GB (Q4_K_M) to 2.4 GB (Q4_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.0 GB | Fits | Get file → | |
| IQ3_XS | 1.6 GB | 2.2 GB | Fits | Get file → | |
| IQ3_S | 1.7 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 1.9 GB | 2.5 GB | Fits | Get file → | |
| Q3_K | 2.0 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 2.6 GB | Fits | Get file → | |
| IQ4_XS | 2.1 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 2.7 GB | Fits | Get file → | |
| Q4_0 | 2.2 GB | 2.8 GB | Fits | Get file → | |
| IQ4_NL | 2.2 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_S | 2.2 GB | 2.8 GB | Fits | Get file → | |
| Q4_K | 2.4 GB | 3.0 GB | Fits | Get file → |
What GPU do you need for Gigax NPC LLM 3 8B?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K (2.4 GB file, about 3.2 GB in use).
Which Gigax NPC LLM 3 8B quant should you choose?
Q4_K_M is the usual starting point for Gigax NPC LLM 3 8B: it balances file size and quality well. Here it is a 0.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gigax NPC LLM 3 8B
How much VRAM does Gigax NPC LLM 3 8B need?
About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Gigax NPC LLM 3 8B on an 8 GB GPU?
Yes, with Q4_K: the 2.4 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gigax NPC LLM 3 8B GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q2_K is 1.4 GB, IQ3_XS is 1.6 GB, IQ3_S is 1.7 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.9 GB and 8 more.
What context length does Gigax NPC LLM 3 8B support?
The GGUF header lists a trained context length of 4,096 tokens (4K).
Where can I download Gigax NPC LLM 3 8B GGUF?
The files are on Hugging Face in the RichardErkhov/Gigax_-_NPC-LLM-3_8B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.