LL

llama instruct sft

LlamaGGUF by sk12154Updated 2024-12-09
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant5.7 GB
Quick answer

llama instruct sft needs about 8.2 GB of memory at Q6_K (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.7 GB (Q5_K_M) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

llama instruct sft is a 8.03B-parameter Llama model in GGUF format, quantized by sk12154. Its trained context length is 128K tokens. The repository has 3 quant files, from 5.7 GB (Q5_K_M) to 8.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

What GPU do you need for llama instruct sft?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which llama instruct sft quant should you choose?

Q6_K (6.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_M at 5.7 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bysk12154
FamilyLlama
Downloads (HF)57
Last updated2024-12-09

Frequently asked questions about llama instruct sft

How much VRAM does llama instruct sft need?

About 8.2 GB at Q6_K with an 8K context window. That is the 6.6 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 llama instruct sft on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llama instruct sft GGUF?

It depends on the quant: Q5_K_M is 5.7 GB, Q6_K is 6.6 GB, Q8_0 is 8.5 GB.

What context length does llama instruct sft support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download llama instruct sft GGUF?

The files are on Hugging Face in the sk12154/llama_instruct_sft repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Llama models

All Llama →

Other small models

All small models →