LL

Llama32_Lora_Merged

LlamaGGUF by hankleetwUpdated 2025-06-01
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.0 GB
Quick answer

Llama32_Lora_Merged needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 1.0 GB (IQ2_XXS) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama32_Lora_Merged is a 3.21B-parameter Llama model in GGUF format, quantized by hankleetw. Its trained context length is 128K tokens. The repository has 9 quant files, from 1.0 GB (IQ2_XXS) to 6.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS1.0 GB 2.5 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_M1.7 GB 3.1 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
BF166.4 GB 7.9 GB
Tight Get file →
F166.4 GB 7.9 GB
Tight Get file →

What GPU do you need for Llama32_Lora_Merged?

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 Q4_K_M (2.0 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.4 GB file, about 7.9 GB in use).

Which Llama32_Lora_Merged quant should you choose?

Q4_K_M is the usual starting point for Llama32_Lora_Merged: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.4 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 IQ2_XXS at 1.0 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
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byhankleetw
FamilyLlama
Downloads (HF)37
Last updated2025-06-01

Frequently asked questions about Llama32_Lora_Merged

How much VRAM does Llama32_Lora_Merged need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Llama32_Lora_Merged on an 8 GB GPU?

Yes, with BF16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama32_Lora_Merged GGUF?

It depends on the quant: IQ2_XXS is 1.0 GB, Q3_K_S is 1.5 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.7 GB, Q4_K_M is 2.0 GB, Q4_K_M is 2.0 GB and 3 more.

What context length does Llama32_Lora_Merged support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Llama32_Lora_Merged GGUF?

The files are on Hugging Face in the hankleetw/llama32_lora_merged 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 from hankleetw

All by hankleetw →

More Llama models

All Llama →

Other tiny models

All tiny models →