lb reranker 0.5B v1.0 needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.3 GB (IQ2_M) to 2.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
Lightblue LB Reranker 0.5B v1.0 – a 0.5B parameter query‑to‑text relevance model
The LB Reranker is a 0.5B parameter model fine‑tuned from Qwen/Qwen2.5‑0.5B‑Instruct. It outputs a score between 1 and 7 to indicate relevance of a query to a text passage. The model is trained on data in over 95 languages.
Good at
- Ranking query‑context pairs
- Embedding generation
- Code snippet reranking
Limits
- No vision support
- Requires 8 k context for memory estimates
- Apache‑2.0 license
Best for
- Retrieval‑augmented generation
- Document relevance scoring
- Code snippet evaluation
Who it’s for. Developers building retrieval‑based systems or content ranking pipelines. Researchers needing a lightweight reranker with multilingual coverage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ3_XS | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q2_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q2_K_L | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ3_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ4_XS | 0.3 GB | 1.0 GB | Fits | Get file → | |
| IQ4_NL | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_XL | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_1 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q6_K_L | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| F16 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| F32 | 2.0 GB | 2.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (0.35 GB file, ~1 GB memory). For 4 GB VRAM, use IQ3_XS (0.34 GB file, ~0.9 GB memory). For 2 GB VRAM, use IQ2_M (0.33 GB file, ~0.9 GB memory).
What GPU do you need for lb reranker 0.5B v1.0?
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 (2.0 GB file, about 2.6 GB in use).
Which lb reranker 0.5B v1.0 quant should you choose?
Q4_K_M is the usual starting point for lb reranker 0.5B v1.0: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.5 GB, about 1.3 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_M at 0.3 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 lb reranker 0.5B v1.0
How much VRAM does lb reranker 0.5B v1.0 need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 lb reranker 0.5B v1.0 on an 8 GB GPU?
Yes, with F32: the 2.0 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of lb reranker 0.5B v1.0 GGUF?
It depends on the quant: IQ2_M is 0.3 GB, Q3_K_S is 0.3 GB, IQ3_XS is 0.3 GB, Q2_K is 0.3 GB, Q2_K_L is 0.3 GB, IQ3_M is 0.3 GB and 18 more.
What context length does lb reranker 0.5B v1.0 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download lb reranker 0.5B v1.0 GGUF?
The files are on Hugging Face in the bartowski/lb-reranker-0.5B-v1.0-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 lb reranker 0.5B v1.0 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 4 GB VRAM?
Yes, use the IQ3_XS or IQ2_M quantizations, which require about 0.9 GB memory at 8 k context.
Does this model support image inputs?
No, the model only processes text and outputs a numeric relevance score.
Is the model free to use?
Yes, it is licensed under Apache‑2.0 and can be used in commercial projects.