SI

SILMA Kashif 2B Instruct v1.0

SilmaGGUF by tensorblockUpdated 2026-01-27
Download on Hugging Face
Parameters2.61B
Context12K
Layers26
Architecturegemma2
Smallest quant1.2 GB
Quick answer

SILMA Kashif 2B Instruct v1.0 needs about 2.6 GB of memory at Q2_K (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.2 GB (Q2_K) to 1.5 GB (Q3_K_M).

SILMA Kashif 2B Instruct v1.0 is a 2.61B-parameter Silma model in GGUF format, quantized by tensorblock. Its trained context length is 12K tokens. The repository has 2 quant files, from 1.2 GB (Q2_K) to 1.5 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 2.6 GB
Fits Get file →
Q3_K_M1.5 GB 2.8 GB
Fits Get file →

What GPU do you need for SILMA Kashif 2B Instruct v1.0?

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 Q3_K_M (1.5 GB file, about 2.8 GB in use).

Which SILMA Kashif 2B Instruct v1.0 quant should you choose?

Q2_K (1.2 GB) is the middle option in this repository. 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

Architecturegemma2
Parameters2.61B
Layers26
Trained context12,288 tokens
KV cache (fp16)104 KB per token

Source

Quantized bytensorblock
FamilySilma
Licensegemma
Downloads (HF)101
Last updated2026-01-27

Frequently asked questions about SILMA Kashif 2B Instruct v1.0

How much VRAM does SILMA Kashif 2B Instruct v1.0 need?

About 2.6 GB at Q2_K with an 8K context window. That is the 1.2 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 SILMA Kashif 2B Instruct v1.0 on an 8 GB GPU?

Yes, with Q3_K_M: the 1.5 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SILMA Kashif 2B Instruct v1.0 GGUF?

It depends on the quant: Q2_K is 1.2 GB, Q3_K_M is 1.5 GB.

What context length does SILMA Kashif 2B Instruct v1.0 support?

The GGUF header lists a trained context length of 12,288 tokens (12K). The KV cache grows with the context you use: about 0.9 GB at 8K and 1.3 GB at 12K.

Where can I download SILMA Kashif 2B Instruct v1.0 GGUF?

The files are on Hugging Face in the tensorblock/SILMA-Kashif-2B-Instruct-v1.0-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 SILMA Kashif 2B Instruct v1.0 use?

Hugging Face lists the license as gemma. 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 SILMA-Kashif-2B-Instruct-v1.0

Similar models

Browse all →

More from tensorblock

All by tensorblock →

More Silma models

All Silma →

Other tiny models

All tiny models →