KaLM Embedding Gemma3 12B 2511 needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
KaLM Embedding Gemma3 12B 2511 – 3840‑dimensional embedding model
KaLM Embedding Gemma3 12B 2511 delivers 3840‑dimensional embeddings from up to 32k input tokens. The model is based on the Gemma architecture and contains 11.8B parameters. It is optimized for embedding tasks and supports sentence‑transformers and vLLM usage.
Good at
- High‑dimensional embeddings
- Large context handling
- Efficient inference
Limits
- No text generation capability
- License type is other
- No vision support
Best for
- Embedding search pipelines
- Semantic similarity tasks
- Vector database indexing
Who it’s for. Developers building embedding‑based search or recommendation systems. Researchers needing a compact, high‑dimensional embedding model for large‑context inputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_L | 6.5 GB | 10.2 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 10.3 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 12.2 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → |
For 8‑GB VRAM use Q2_K (4.77 GB, 8.5 GB memory). For 12‑GB VRAM use Q4_K_M (7.3 GB, 11 GB memory). For 16‑GB VRAM use Q8_0 (12.51 GB, 16.2 GB memory). Estimates are approximate.
What GPU do you need for KaLM Embedding Gemma3 12B 2511?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
Which KaLM Embedding Gemma3 12B 2511 quant should you choose?
Q4_K_M is the usual starting point for KaLM Embedding Gemma3 12B 2511: it balances file size and quality well. Here it is a 7.3 GB file.
The Q8_0 file is 12.5 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 Q2_K at 4.8 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 KaLM Embedding Gemma3 12B 2511
How much VRAM does KaLM Embedding Gemma3 12B 2511 need?
About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 Embedding Gemma3 12B 2511 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KaLM Embedding Gemma3 12B 2511 GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.0 GB, Q3_K_L is 6.5 GB, IQ4_XS is 6.6 GB, Q4_K_S is 6.9 GB and 5 more.
What context length does KaLM Embedding Gemma3 12B 2511 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download KaLM Embedding Gemma3 12B 2511 GGUF?
The files are on Hugging Face in the mradermacher/KaLM-Embedding-Gemma3-12B-2511-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 Gemma3 12B 2511 use?
Hugging Face lists the license as other. 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 Q2_K quant requires about 8.5 GB memory at 8k context, which fits in 8 GB VRAM with some headroom.
Does this model support text generation?
No, it is an embedding model only and does not generate text.
What is the maximum context length?
The model supports up to 32k input tokens for embedding generation.