TE

migtissera_tess-34b-v1.5b

TessGGUF by TheBlokeUpdated 2024-01-28
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant12.8 GB
Quick answer

migtissera_tess-34b-v1.5b needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 12.8 GB (Q2_K) to 36.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

migtissera_tess-34b-v1.5b – a 34.4B parameter Llama model in GGUF format

migtissera_tess-34b-v1.5b is a 34.4B parameter Llama model. It was trained on a 200K token context and is available in multiple GGUF quantisations. The model is part of the Tess family and is released under an other license.

Good at

  • Large context handling
  • High parameter count
  • Versatile language tasks

Limits

  • No vision support
  • License not specified for commercial use
  • Large memory requirement for higher quants

Best for

  • Research prototypes
  • High‑capacity text generation
  • Fine‑tuning experiments

Who it’s for. Developers and researchers who need a large language model with a 200K token context. The model is suitable for local deployment using llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.8 GB 15.3 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
Q4_019.5 GB 22.0 GB
Too big Get file →
Q4_K_S19.6 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_023.7 GB 26.2 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →
Q8_036.5 GB 39.1 GB
Too big Get file →

For 8 GB VRAM use Q2_K (file size 12.83 GB, estimated memory 15.3 GB). For 12 GB VRAM use Q3_K_S (14.96 GB, 17.5 GB). For 16 GB VRAM use Q4_0 (19.47 GB, 22 GB). Higher quants require proportionally more VRAM.

What GPU do you need for migtissera_tess-34b-v1.5b?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K (12.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which migtissera_tess-34b-v1.5b quant should you choose?

Q4_K_M is the usual starting point for migtissera_tess-34b-v1.5b: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 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 12.8 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

Architecturellama
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byTheBloke
FamilyTess
Licenseother
Downloads (HF)1,705
Last updated2024-01-28

Frequently asked questions about migtissera_tess-34b-v1.5b

How much VRAM does migtissera_tess-34b-v1.5b need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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-34b-v1.5b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of migtissera_tess-34b-v1.5b GGUF?

It depends on the quant: Q2_K is 12.8 GB, Q3_K_S is 15.0 GB, Q3_K_M is 16.7 GB, Q3_K_L is 18.1 GB, Q4_0 is 19.5 GB, Q4_K_S is 19.6 GB and 6 more.

What context length does migtissera_tess-34b-v1.5b support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download migtissera_tess-34b-v1.5b GGUF?

The files are on Hugging Face in the TheBloke/Tess-34B-v1.5b-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-34b-v1.5b 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 Q2_K on 8 GB VRAM?

Yes, Q2_K requires about 15.3 GB of memory at 8 k context, which is within 8 GB VRAM when using efficient batching.

What is the memory requirement for Q4_0?

Q4_0 needs approximately 22 GB of memory at 8 k context, so a GPU with at least 24 GB VRAM is recommended.

Does the model support vision tasks?

No, the model has no vision support.

Other GGUFs of Tess-34B-v1.5b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Tess models

All Tess →

Other large models

All large models →