KA

KaLM Embedding Multilingual Mini Instruct v1.5

KalmGGUF by mradermacherUpdated 2025-07-31
Download on Hugging Face
Parameters494M
Context128K
Layers24
Architectureqwen2
Smallest quant0.3 GB
Quick answer

KaLM Embedding Multilingual Mini Instruct v1.5 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 12 quants, from 0.3 GB (Q3_K_S) to 1.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

KaLM Embedding Multilingual Mini Instruct v1.5 – a lightweight embedding model

KaLM Embedding Multilingual Mini Instruct v1.5 is a 0.494 billion‑parameter model based on Qwen2 architecture. It is optimized for generating embeddings and supports up to 131072 context tokens. The model is released under the MIT license.

Good at

  • Embedding generation
  • Multilingual support
  • Instruction‑guided embeddings

Limits

  • No vision capabilities
  • Requires 8 k context for memory estimates
  • No mixture‑of‑experts

Best for

  • Semantic search
  • Document clustering
  • Retrieval‑augmented generation

Who it’s for. Developers building embedding pipelines who need a small, open‑source model. The model is suitable for research and production environments that require multilingual embedding generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
Q2_K0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.4 GB 1.0 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q3_K_L0.4 GB 1.0 GB
Fits Get file →
Q4_K_S0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q3_K_S or Q2_K (0.34 GB file, ~0.9 GB RAM). If 12 GB VRAM is available, Q4_K_M (0.40 GB file, ~1 GB RAM) offers higher quality. For the highest precision, use F16 (0.99 GB file, ~1.6 GB RAM).

What GPU do you need for KaLM Embedding Multilingual Mini Instruct v1.5?

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 F16 (1.0 GB file, about 1.6 GB in use).

Which KaLM Embedding Multilingual Mini Instruct v1.5 quant should you choose?

Q4_K_M is the usual starting point for KaLM Embedding Multilingual Mini Instruct v1.5: 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 Q3_K_S at 0.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context131,072 tokens
KV cache (fp16)12 KB per token

Frequently asked questions about KaLM Embedding Multilingual Mini Instruct v1.5

How much VRAM does KaLM Embedding Multilingual Mini Instruct v1.5 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 Instruct v1.5 on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 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 Instruct v1.5 GGUF?

It depends on the quant: Q3_K_S is 0.3 GB, Q2_K is 0.3 GB, IQ4_XS is 0.4 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB, Q4_K_S is 0.4 GB and 6 more.

What context length does KaLM Embedding Multilingual Mini Instruct v1.5 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 Instruct v1.5 GGUF?

The files are on Hugging Face in the mradermacher/KaLM-embedding-multilingual-mini-instruct-v1.5-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 Instruct v1.5 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, the Q3_K_S and Q2_K quantizations are 0.34 GB and require about 0.9 GB RAM at 8 k context.

Does the model support vision tasks?

No, the model only provides embedding capabilities and has no vision support.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of KaLM-embedding-multilingual-mini-instruct-v1.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kalm models

All Kalm →

Other tiny models

All tiny models →