MX

mxbai-rerank-large-v2

MxbaiGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant0.4 GB
Quick answer

mxbai-rerank-large-v2 needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 34 quants, from 0.4 GB (IQ1_S) to 3.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

mxbai-rerank-large-v2 – a 1.54B parameter embedding model

mxbai-rerank-large-v2 is a 1.54B parameter model based on the qwen2 architecture. It is trained on 32768 context tokens and supports embedding and tools. The model is released under the apache-2.0 license.

Good at

  • Embedding generation
  • Tool integration
  • Re-ranking tasks

Limits

  • No vision support
  • Requires 8k context for estimates
  • License is apache-2.0

Best for

  • Embedding search engines
  • Re-ranking search results
  • Tool‑aware LLM pipelines

Who it’s for. Developers building search or ranking systems that need a lightweight embedding model. The model is suitable for applications that require tool integration and can run on GPUs or CPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.4 GB 1.2 GB
Fits Get file →
IQ1_M0.5 GB 1.2 GB
Fits Get file →
TQ1_00.5 GB 1.2 GB
Fits Get file →
IQ2_XXS0.5 GB 1.2 GB
Fits Get file →
TQ2_00.5 GB 1.3 GB
Fits Get file →
IQ2_XS0.6 GB 1.3 GB
Fits Get file →
IQ2_S0.6 GB 1.3 GB
Fits Get file →
IQ2_M0.6 GB 1.3 GB
Fits Get file →
Q2_K_S0.6 GB 1.4 GB
Fits Get file →
IQ3_XXS0.7 GB 1.4 GB
Fits Get file →
IQ3_XS0.7 GB 1.5 GB
Fits Get file →
Q3_K_S0.8 GB 1.5 GB
Fits Get file →
IQ3_S0.8 GB 1.5 GB
Fits Get file →
IQ3_M0.8 GB 1.5 GB
Fits Get file →
Q3_K_M0.8 GB 1.6 GB
Fits Get file →
Q4_00.9 GB 1.6 GB
Fits Get file →
IQ4_XS0.9 GB 1.6 GB
Fits Get file →
IQ4_NL0.9 GB 1.7 GB
Fits Get file →
Q4_K_S0.9 GB 1.7 GB
Fits Get file →
Q4_11.0 GB 1.7 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
Q5_01.1 GB 1.8 GB
Fits Get file →
Q5_K_S1.1 GB 1.8 GB
Fits Get file →
Q5_K_M1.1 GB 1.9 GB
Fits Get file →
Q5_11.2 GB 1.9 GB
Fits Get file →
BF161.3 GB 2.0 GB
Fits Get file →
F161.3 GB 2.0 GB
Fits Get file →
Q6_K_M1.3 GB 2.0 GB
Fits Get file →
BF161.5 GB 2.3 GB
Fits Get file →
F161.5 GB 2.3 GB
Fits Get file →
Q8_01.6 GB 2.4 GB
Fits Get file →
BF161.9 GB 2.6 GB
Fits Get file →
F161.9 GB 2.6 GB
Fits Get file →
BF163.1 GB 3.8 GB
Fits Get file →

For 8 GB VRAM use Q4_K_S (file size 0.94 GB, memory 1.7 GB) or Q4_0 (0.87 GB, 1.6 GB). For 4 GB VRAM use IQ4_XS (0.90 GB, 1.6 GB) or IQ4_NL (0.94 GB, 1.7 GB). For 2 GB VRAM use IQ1_S (0.44 GB, 1.2 GB).

What GPU do you need for mxbai-rerank-large-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 BF16 (3.1 GB file, about 3.8 GB in use).

Which mxbai-rerank-large-v2 quant should you choose?

Q4_K_M is the usual starting point for mxbai-rerank-large-v2: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.6 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 IQ1_S at 0.4 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

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byMungert
FamilyMxbai
Licenseapache-2.0
Downloads (HF)866
Last updated2025-09-24

Frequently asked questions about mxbai-rerank-large-v2

How much VRAM does mxbai-rerank-large-v2 need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 mxbai-rerank-large-v2 on an 8 GB GPU?

Yes, with BF16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mxbai-rerank-large-v2 GGUF?

It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, TQ1_0 is 0.5 GB, IQ2_XXS is 0.5 GB, TQ2_0 is 0.5 GB, IQ2_XS is 0.6 GB and 28 more.

What context length does mxbai-rerank-large-v2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download mxbai-rerank-large-v2 GGUF?

The files are on Hugging Face in the Mungert/mxbai-rerank-large-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 mxbai-rerank-large-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 mxbai-rerank-large-v2 on 8 GB VRAM?

Yes, use a quant like Q4_K_S or Q4_0, which require about 1.6–1.7 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Mxbai models

All Mxbai →

Other tiny models

All tiny models →