all-MiniLM-L6-v2 needs about 0.6 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.0 GB (Q2_K) to 0.1 GB (F32).
Compact sentence encoder for semantic tasks
all-MiniLM-L6-v2 is a lightweight BERT‑based model that maps sentences to 384‑dimensional vectors. It is trained with a contrastive objective on a large sentence pair dataset. The model is available in GGUF format for efficient inference.
Good at
- Fast embedding generation
- Low memory footprint
- Supports short text encoding
Limits
- No vision support
- Truncates input longer than 256 word pieces
- Requires 8k context for memory estimates
Best for
- Semantic search
- Clustering short texts
- Similarity ranking
Who it’s for. Developers building search engines or recommendation systems that need quick sentence embeddings. Researchers requiring a small, efficient model for prototype experiments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_L | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q6_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| F16 | 0.0 GB | 0.6 GB | Fits | Get file → | |
| F32 | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q5_K_M; file size 0.02 GB and memory estimate 0.6 GB. For 4 GB VRAM, Q2_K or Q3_K_S are suitable. Higher precision models like F32 need 0.09 GB file size and 0.7 GB memory.
What GPU do you need for all-MiniLM-L6-v2?
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 F32 (0.1 GB file, about 0.7 GB in use).
Which all-MiniLM-L6-v2 quant should you choose?
Q4_K_M is the usual starting point for all-MiniLM-L6-v2: it balances file size and quality well. Here it is a 0.0 GB file.
The Q8_0 file is 0.0 GB, about 1.2 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 0.0 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
Source
Frequently asked questions about all-MiniLM-L6-v2
How much VRAM does all-MiniLM-L6-v2 need?
About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.0 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 all-MiniLM-L6-v2 on an 8 GB GPU?
Yes, with F32: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of all-MiniLM-L6-v2 GGUF?
It depends on the quant: Q2_K is 0.0 GB, Q3_K_S is 0.0 GB, Q4_0 is 0.0 GB, Q3_K_M is 0.0 GB, Q3_K_L is 0.0 GB, Q4_K_S is 0.0 GB and 8 more.
What context length does all-MiniLM-L6-v2 support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.
Where can I download all-MiniLM-L6-v2 GGUF?
The files are on Hugging Face in the leliuga/all-MiniLM-L6-v2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does all-MiniLM-L6-v2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations keeps memory usage around 0.6 GB.
Does this model support image inputs?
No, it is a text‑only sentence encoder.
What license applies?
The model is released under the apache-2.0 license.