LO

Loki v5.2 i1

LokiGGUF by mradermacherUpdated 2024-08-23
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Loki v5.2 i1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 1.6 GB (IQ1_S) to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

7.24B parameter Llama model with 32k context

Loki v5.2 i1 is a 7.24B parameter Llama architecture model. It supports a 32768 token context window. The model is available in multiple GGUF quantizations ranging from IQ1_S to Q6_K.

Good at

  • Large context handling
  • High parameter count
  • Multiple quant options

Limits

  • No license information
  • No vision support
  • No mixture of experts

Best for

  • Chatting with long context
  • Fine‑tuning on custom data
  • Running on low‑VRAM devices

Who it’s for. Developers and researchers who need a large Llama model with extended context. The model is suitable for local deployment via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →

For 8 GB VRAM, use IQ4_XS (est. 5.5 GB) or Q4_K_S (est. 5.7 GB). If 12 GB VRAM is available, Q5_K_S (est. 6.6 GB) or Q5_K_M (est. 6.7 GB) provide higher quality. For 16 GB VRAM, Q6_K (est. 7.5 GB) is recommended.

What GPU do you need for Loki v5.2 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_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).

Which Loki v5.2 i1 quant should you choose?

Q4_K_M is the usual starting point for Loki v5.2 i1: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is IQ1_S at 1.6 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLoki
Downloads (HF)1,211
Last updated2024-08-23

Frequently asked questions about Loki v5.2 i1

How much VRAM does Loki v5.2 i1 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 v5.2 i1 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Loki v5.2 i1 GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 15 more.

What context length does Loki v5.2 i1 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 Loki v5.2 i1 GGUF?

The files are on Hugging Face in the mradermacher/Loki-v5.2-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, use IQ4_XS or Q4_K_S quantizations, which estimate 5.5–5.7 GB memory at 8k context.

Does this model support vision?

No, the model has no vision capabilities.

Is the model a mixture of experts?

No, it is a standard Llama architecture without MoE.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Loki models

All Loki →

Other small models

All small models →