LL

tsukasa llama 3 8b qlora

LlamaGGUF by mradermacherUpdated 2024-05-05
Download on Hugging Face
Parameters8B
Context32K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

tsukasa llama 3 8b qlora needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 3.2 GB (Q2_K) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

tsukasa llama 3 8b qlora – a fine‑tuned 8B Llama 3 model

tsukasa llama 3 8b qlora is a QLoRA‑fine‑tuned version of Meta Llama 3 8B Instruct. It was trained on pippa and limarp with a 32k context window. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • 32k context generation
  • QLoRA fine‑tuning

Limits

  • No vision support
  • No license information provided
  • No language metadata

Best for

  • Chatbots needing long context
  • Custom instruction generation
  • Fine‑tuned Llama 3 use cases

Who it’s for. Developers and researchers who want a compact, fine‑tuned Llama 3 model for instruction‑based tasks. The model is suitable for local deployment with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
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 →

For 8 GB VRAM, use Q4_K_S (file size 4.69 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q5_K_S (5.6 GB, 7.2 GB memory) or Q5_K_M (5.73 GB, 7.3 GB memory). For 16 GB VRAM, Q6_K (6.6 GB, 8.2 GB memory) or Q8_0 (8.54 GB, 10.1 GB memory). Estimates are approximate.

What GPU do you need for tsukasa llama 3 8b qlora?

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: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 GB in use).
  • 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 tsukasa llama 3 8b qlora quant should you choose?

Q4_K_M is the usual starting point for tsukasa llama 3 8b qlora: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)1,227
Last updated2024-05-05

Frequently asked questions about tsukasa llama 3 8b qlora

How much VRAM does tsukasa llama 3 8b qlora need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 tsukasa llama 3 8b qlora 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 tsukasa llama 3 8b qlora GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB and 8 more.

What context length does tsukasa llama 3 8b qlora support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 tsukasa llama 3 8b qlora GGUF?

The files are on Hugging Face in the mradermacher/tsukasa-llama-3-8b-qlora-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run tsukasa llama 3 8b qlora on 8 GB VRAM?

Yes, the Q4_K_S quantization requires about 6.3 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does this model support image inputs?

No, the model has no vision capabilities.

What context length does it support?

It supports up to 32,768 tokens, as trained on a 32k context window.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →