KaLM Embedding Multilingual Mini v1 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 25 quants, from 0.0 GB to 0.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
KaLM Embedding Multilingual Mini v1 – lightweight multilingual embedding model
KaLM Embedding Multilingual Mini v1 is a 0.494 billion‑parameter embedding model based on Qwen2. It supports up to 131072 context tokens and is released under the MIT license. The model is optimized for generating sentence embeddings in multiple languages.
Good at
- Fast embedding generation
- Low memory footprint
- Open‑source and MIT licensed
Limits
- No language list provided
- No vision support
- Requires transformers>=4.37.0
Best for
- Text similarity search
- Semantic clustering
- Embedding‑based retrieval
Who it’s for. Developers needing a small, fast embedding model for multilingual text. Researchers and engineers can integrate it into pipelines that require sentence embeddings without large GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ1_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ1_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ2_XS | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ2_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ2_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q2_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ3_XXS | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ3_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 → | |
| 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 → | |
| 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_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_S | 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 → |
For 8 GB VRAM, use Q4_K_S (0.39 GB file, ~1 GB RAM). For 4 GB VRAM, use IQ3_S (0.34 GB file, ~0.9 GB RAM). For 2 GB VRAM, use IQ1_S (0.32 GB file, ~0.9 GB RAM). Estimates are approximate.
What GPU do you need for KaLM Embedding Multilingual Mini v1?
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 Q6_K (0.5 GB file, about 1.1 GB in use).
Which KaLM Embedding Multilingual Mini v1 quant should you choose?
Q4_K_M is the usual starting point for KaLM Embedding Multilingual Mini v1: it balances file size and quality well. Here it is a 0.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about KaLM Embedding Multilingual Mini v1
How much VRAM does KaLM Embedding Multilingual Mini v1 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 KaLM Embedding Multilingual Mini v1 on an 8 GB GPU?
Yes, with Q6_K: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of KaLM Embedding Multilingual Mini v1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.3 GB, IQ2_S is 0.3 GB and 19 more.
What context length does KaLM Embedding Multilingual Mini v1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download KaLM Embedding Multilingual Mini v1 GGUF?
The files are on Hugging Face in the mradermacher/KaLM-embedding-multilingual-mini-v1-i1-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 KaLM Embedding Multilingual Mini v1 use?
Hugging Face lists the license as mit. 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, a Q4_K_S quant (~0.39 GB) will fit and uses about 1 GB RAM.
Does the model support vision tasks?
No, it is an embedding model with no vision capability.
What license does it use?
The model is released under the MIT license.