LO

Loki base i1

LokiGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters8.03B
Context1024K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Loki base i1 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 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

8.03B parameter Llama-based model in GGUF format

Loki base i1 is an 8.03B parameter Llama model distributed as GGUF files. It offers a range of quantizations from IQ1_S to Q6_K, allowing users to balance file size and memory usage. The model supports a context length of 1,048,576 tokens.

Good at

  • Large context handling
  • Flexible quantization options
  • Compact file sizes

Limits

  • No license specified
  • No vision capabilities
  • Context limited to 1,048,576 tokens

Best for

  • Long-form text generation
  • Fine-tuning on local hardware
  • Research on quantization effects

Who it’s for. Developers and researchers who need a large Llama model with multiple quantization choices for local deployment. The model is suitable for those who can manage the memory requirements of higher precision quants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 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_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 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 →

For 8 GB VRAM, use IQ2_S (est. 4.3 GB) or Q2_K (est. 4.8 GB). If 12 GB VRAM is available, Q3_K_M (est. 5.6 GB) or Q4_K_M (est. 6.5 GB) provide higher precision. For 16 GB VRAM, Q5_K_M (est. 7.3 GB) or Q6_K (est. 8.2 GB) are suitable. Estimates are approximate.

What GPU do you need for Loki base i1?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 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 Q6_K (6.6 GB file, about 8.2 GB in use).

Which Loki base i1 quant should you choose?

Q4_K_M is the usual starting point for Loki base i1: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters8.03B
Layers32
Trained context1,048,576 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLoki
Downloads (HF)771
Last updated2024-08-02

Frequently asked questions about Loki base i1

How much VRAM does Loki base i1 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 Loki base i1 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 Loki base i1 GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Loki base i1 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). 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 Loki base i1 GGUF?

The files are on Hugging Face in the mradermacher/Loki-base-i1-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 this model on 8 GB VRAM?

Yes, with IQ2_S (est. 4.3 GB) or Q2_K (est. 4.8 GB).

Does this model support vision tasks?

No, it is a text-only Llama model.

What is the maximum context length?

The model supports up to 1,048,576 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Loki models

All Loki →

Other small models

All small models →