TE

migtissera_tess-xs-v1.1

TessGGUF by TheBlokeUpdated 2023-11-22
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

migtissera_tess-xs-v1.1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

migtissera_tess-xs-v1.1 – 7.24B Llama model in GGUF format

migtissera_tess-xs-v1.1 is a 7.24B parameter Llama model released by TheBloke. It supports a 32,768 token context window and is licensed under apache-2.0. The model is available in multiple GGUF quantisations for CPU and GPU inference.

Good at

  • General purpose text generation
  • Supports 32k context
  • Compatible with llama.cpp and other GGUF clients

Limits

  • No vision support
  • Experimental version, use Tess-XS-v1.3-yarn-128K instead
  • Requires GPU or CPU with sufficient VRAM

Best for

  • Chatbots on local machines
  • Fine‑tuning small datasets
  • Rapid prototyping of LLM applications

Who it’s for. Developers and researchers who need a lightweight Llama model for local inference. The model is suitable for those who prefer GGUF format and have access to GPU or CPU resources that can handle the required memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, Q4_0 (file size 4.11 GB, memory 5.7 GB) or Q4_K_S (4.14 GB, 5.7 GB) are suitable. If 12 GB VRAM is available, Q5_0 (5 GB, 6.6 GB) or Q5_K_M (5.13 GB, 6.7 GB) can be used. For 16 GB VRAM, Q6_K (5.94 GB, 7.5 GB) or Q8_0 (7.7 GB, 9.3 GB) provide higher precision.

What GPU do you need for migtissera_tess-xs-v1.1?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which migtissera_tess-xs-v1.1 quant should you choose?

Q4_K_M is the usual starting point for migtissera_tess-xs-v1.1: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 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 3.1 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

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheBloke
FamilyTess
Licenseapache-2.0
Downloads (HF)1,703
Last updated2023-11-22

Frequently asked questions about migtissera_tess-xs-v1.1

How much VRAM does migtissera_tess-xs-v1.1 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 migtissera_tess-xs-v1.1 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of migtissera_tess-xs-v1.1 GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.

What context length does migtissera_tess-xs-v1.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 migtissera_tess-xs-v1.1 GGUF?

The files are on Hugging Face in the TheBloke/Tess-XS-v1.1-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 migtissera_tess-xs-v1.1 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, use Q4_0 or Q4_K_S quantisations; each requires about 5.7 GB of VRAM at 8k context.

What is the maximum context length?

The model supports 32,768 tokens.

Is this model suitable for vision tasks?

No, it does not support vision capabilities.

Other GGUFs of Tess-XS-v1.1

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Tess models

All Tess →

Other small models

All small models →