Tess-4.5-27B needs about 4.7 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.0 GB (Q4_K_M) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
27‑billion‑parameter Qwen3.8‑based model for engineering tasks
Tess‑4.5 is a 27‑billion‑parameter open‑weights model built on Qwen3.8‑27B. It reasons step‑by‑step, works with local tools and files, and runs on a single GPU or laptop. It supports vision and uses a multi‑token‑prediction draft head for faster generation.
Good at
- Reasoning through complex tasks
- Tool‑aware execution
- Vision‑enabled interactions
Limits
- No vision support on older llama.cpp builds
- Requires recent llama.cpp for draft head
- License is Apache‑2.0
Best for
- Local code generation
- Engineering problem solving
- Tool‑centric workflows
Who it’s for. Developers and engineers who need a local LLM that can read its environment, use provided tools, and produce concise answers. Ideal for single‑GPU or laptop deployments where open‑weight models are preferred.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.0 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.8 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.3 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (2.03 GB file, ~4.7 GB memory at 8 k context). For 24 GB VRAM use Q6_K (22.08 GB file, ~24.8 GB memory) or Q8_0 (28.6 GB file, ~31.3 GB memory). Larger VRAM allows the higher‑quality Q8_0 quant.
What GPU do you need for Tess-4.5-27B?
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 Q8_0 (3.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.5 GB file, about 19.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.3 GB in use).
Which Tess-4.5-27B quant should you choose?
Q4_K_M is the usual starting point for Tess-4.5-27B: it balances file size and quality well. Here it is a 2.0 GB file.
The Q8_0 file is 3.2 GB, about 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Tess-4.5-27B
How much VRAM does Tess-4.5-27B need?
About 4.7 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Tess-4.5-27B on an 8 GB GPU?
Yes, with Q8_0: the 3.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Tess-4.5-27B GGUF?
It depends on the quant: Q4_K_M is 2.0 GB, Q8_0 is 3.2 GB, Q4_K_M is 16.5 GB, Q6_K is 22.1 GB, Q8_0 is 28.6 GB.
What context length does Tess-4.5-27B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Tess-4.5-27B GGUF?
The files are on Hugging Face in the migtissera/Tess-4.5-27B-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 Tess-4.5-27B 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 Tess‑4.5 on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 4.7 GB of VRAM at 8 k context.
Does Tess‑4.5 support vision?
Yes, it has vision capabilities, but older llama.cpp builds may not support the projector.
What draft head does Tess‑4.5 use?
It uses a multi‑token‑prediction draft head for faster generation, available in the GGUF repo.