KA

KaLM Reranker V1 Small

KalmGGUF by KaLM-EmbeddingUpdated 2026-07-07
Download on Hugging Face
Parameters1.7B
Context32K
Layers26
Architecturet5gemma2
Smallest quant1.3 GB
Quick answer

KaLM Reranker V1 Small needs about 2.0 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

KaLM Reranker V1 Small is a 1.7B-parameter Kalm model in GGUF format, quantized by KaLM-Embedding. Its trained context length is 32K tokens. The repository has 1 quant file, from 1.3 GB (Q4_K_M) to 1.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 2.0 GB
Fits Get file →

What GPU do you need for KaLM Reranker V1 Small?

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 Q4_K_M (1.3 GB file, about 2.0 GB in use).

Which KaLM Reranker V1 Small quant should you choose?

Q4_K_M is the usual starting point for KaLM Reranker V1 Small: it balances file size and quality well. Here it is a 1.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5gemma2
Parameters1.7B
Layers26
Trained context32,768 tokens
KV cache (fp16)26 KB per token

Source

Quantized byKaLM-Embedding
FamilyKalm
Licenseapache-2.0
Downloads (HF)118
Last updated2026-07-07

Frequently asked questions about KaLM Reranker V1 Small

How much VRAM does KaLM Reranker V1 Small need?

About 2.0 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Reranker V1 Small on an 8 GB GPU?

Yes, with Q4_K_M: the 1.3 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KaLM Reranker V1 Small GGUF?

It depends on the quant: Q4_K_M is 1.3 GB.

What context length does KaLM Reranker V1 Small 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 KaLM Reranker V1 Small GGUF?

The files are on Hugging Face in the KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 Reranker V1 Small 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.

Other GGUFs of KaLM-Reranker-V1-Small

Similar models

Browse all →

More from KaLM-Embedding

All by KaLM-Embedding →

More Kalm models

All Kalm →

Other tiny models

All tiny models →