JA

pszemraj jamba 900M v0.13 KIx2

JambaGGUF by bartowskiUpdated 2025-07-10
Download on Hugging Face
Parameters888M
Context16K
Layers12
Architecturejamba
Smallest quant0.4 GB
Quick answer

pszemraj jamba 900M v0.13 KIx2 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 20 quants, from 0.4 GB (IQ3_XS) to 1.8 GB (BF16).

pszemraj jamba 900M v0.13 KIx2 – a small MoE model

pszemraj jamba 900M v0.13 KIx2 is a 0.888B parameter model with 12 layers and 8 experts. It was pretrained on 20B tokens and supports a context length of 16384 tokens. The model is released under the Apache‑2.0 license.

Good at

  • MoE architecture for efficient inference
  • Large context support
  • Compact size for low‑resource setups

Limits

  • No vision support
  • Requires 8k+ context for full performance
  • No official benchmark scores

Best for

  • Local LLM inference on modest GPUs
  • Rapid prototyping of MoE models
  • Educational demonstrations of small‑scale MoE

Who it’s for. Developers and researchers who need a lightweight MoE model for local deployment. The model is suitable for experimentation and educational purposes, especially on systems with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.3 GB
Fits Get file →
IQ3_M0.4 GB 1.3 GB
Fits Get file →
Q3_K_M0.4 GB 1.3 GB
Fits Get file →
Q3_K_L0.4 GB 1.3 GB
Fits Get file →
Q3_K_XL0.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
IQ4_NL0.5 GB 1.4 GB
Fits Get file →
Q4_00.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_10.6 GB 1.5 GB
Fits Get file →
Q4_K_L0.6 GB 1.5 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q5_K_L0.7 GB 1.6 GB
Fits Get file →
Q6_K0.7 GB 1.6 GB
Fits Get file →
Q6_K_L0.8 GB 1.7 GB
Fits Get file →
Q8_00.9 GB 1.8 GB
Fits Get file →
BF161.8 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.54 GB, 1.4 GB memory at 8k context) or Q4_K_S (0.53 GB, 1.4 GB memory). If 4 GB VRAM is available, Q3_K_S (0.41 GB, 1.3 GB memory) is a good balance. For the smallest footprint, IQ3_XS (0.40 GB, 1.3 GB memory) fits easily on low‑end hardware.

What GPU do you need for pszemraj jamba 900M v0.13 KIx2?

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 BF16 (1.8 GB file, about 2.7 GB in use).

Which pszemraj jamba 900M v0.13 KIx2 quant should you choose?

Q4_K_M is the usual starting point for pszemraj jamba 900M v0.13 KIx2: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.9 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 IQ3_XS at 0.4 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

Architecturejamba
Parameters888M (approximate, mixture of experts)
Layers12
Trained context16,384 tokens
KV cache (fp16)48 KB per token

Source

Quantized bybartowski
FamilyJamba
Licenseapache-2.0
Downloads (HF)704
Last updated2025-07-10

Frequently asked questions about pszemraj jamba 900M v0.13 KIx2

How much VRAM does pszemraj jamba 900M v0.13 KIx2 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 pszemraj jamba 900M v0.13 KIx2 on an 8 GB GPU?

Yes, with BF16: the 1.8 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of pszemraj jamba 900M v0.13 KIx2 GGUF?

It depends on the quant: IQ3_XS is 0.4 GB, Q3_K_S is 0.4 GB, IQ3_M is 0.4 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB, Q3_K_XL is 0.5 GB and 14 more.

What context length does pszemraj jamba 900M v0.13 KIx2 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.8 GB at 16K.

Where can I download pszemraj jamba 900M v0.13 KIx2 GGUF?

The files are on Hugging Face in the bartowski/pszemraj_jamba-900M-v0.13-KIx2-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 pszemraj jamba 900M v0.13 KIx2 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.

Can I run this model on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 1.4 GB of VRAM at 8k context, leaving headroom for other processes.

Does this model support vision tasks?

No, the model has no vision capabilities and is text‑only.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Jamba models

All Jamba →

Other tiny models

All tiny models →