SA

samai 9b

SamaiGGUF by tchbcbUpdated 2026-09-25
Download on Hugging Face
Parameters9.2B
Context256K
Layers32
Architectureqwen35
Smallest quant0.2 GB
Quick answer

samai 9b needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 9 quants, from 0.2 GB to 7.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Samai 9B – a 9.2B parameter Qwen‑35 model with vision support

Samai 9B is a 9.2B parameter model based on the Qwen‑35 architecture. It supports vision tasks and has a trained context of 262144 tokens. The model is available in several GGUF quantizations.

Good at

  • Vision tasks
  • Long‑context generation
  • Multimodal interactions

Limits

  • No license information provided
  • Vision only, no text‑only specializations
  • Large memory requirement for higher quantizations

Best for

  • Image captioning
  • Multimodal chat applications
  • Long‑form content creation

Who it’s for. Developers needing a multimodal LLM with a large context window. Suitable for projects that require vision capabilities and can accommodate the model’s memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.8 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q4_K_M5.8 GB 7.4 GB
Tight Get file →
—6.5 GB 8.1 GB
Too big Get file →
—6.5 GB 8.1 GB
Too big Get file →
—6.9 GB 8.5 GB
Too big Get file →
—6.9 GB 8.5 GB
Too big Get file →
—7.1 GB 8.7 GB
Too big Get file →
—7.1 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quantized file of 5.63 GB, which estimates 7.2 GB memory at 8 k context. If more VRAM is available, the 5.78 GB Q4_K_M file uses 7.4 GB memory. Smaller unknown quant files (0.23 GB) use 1.8 GB memory but may lack full functionality.

What GPU do you need for samai 9b?

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 the main file (0.2 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.8 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.1 GB file, about 8.7 GB in use).

Which samai 9b quant should you choose?

Q4_K_M is the usual starting point for samai 9b: it balances file size and quality well. Here it is a 5.6 GB file.

If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9.2B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bytchbcb
FamilySamai
Repositorytchbcb/samai-9b
Downloads (HF)133
Last updated2026-09-25

Frequently asked questions about samai 9b

How much VRAM does samai 9b need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 samai 9b on an 8 GB GPU?

Yes, with Q4_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of samai 9b GGUF?

It depends on the quant: file is 0.2 GB, Q4_K_M is 5.6 GB, Q4_K_M is 5.8 GB, file is 6.5 GB, file is 6.5 GB, file is 6.9 GB and 3 more.

What context length does samai 9b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download samai 9b GGUF?

The files are on Hugging Face in the tchbcb/samai-9b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Samai 9B on 8 GB VRAM?

Yes, the Q4_K_M quantized file of 5.63 GB uses about 7.2 GB memory at 8 k context, fitting within 8 GB VRAM.

Does Samai 9B support text-only tasks?

The model has vision capabilities but is not specialized for text-only tasks; it can still perform text generation.

What is the trained context length of Samai 9B?

The model was trained with a context of 262144 tokens.

Similar models

Browse all →

More from tchbcb

All by tchbcb →

More Samai models

All Samai →

Other small models

All small models →