Qwen3.8 27B Artemis needs about 4.0 GB of memory at Q4_0 (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.3 GB (Q4_0) to 7.8 GB (IQ2_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Qwen3.8 27B Artemis – dense vision‑language model for local tool calling and agents
Qwen3.8 27B Artemis is a 26.9B‑parameter dense model with 262144‑token context. It supports reasoning, tool‑calling and vision tasks. The model is released under Apache‑2.0 and is compatible with llama.cpp and other open‑source harnesses.
Good at
- Vision‑language understanding
- Tool‑calling
- Long‑horizon agentic tasks
Limits
- No vision support without projector file
- Requires llama.cpp b11617 or newer
- Large context length 262144 tokens
Best for
- Local agent execution
- Tool‑calling workflows
- Vision‑based reasoning
Who it’s for. Developers building local LLM agents that need vision and tool integration. Suitable for users who prefer open‑source models with Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.3 GB | 4.0 GB | Fits | Get file → | |
| IQ2_XXS | 7.8 GB | 10.5 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_0 quant file (1.34 GB, ~4 GB memory at 8k context). For 10.5 GB memory use the IQ2_XXS quant file (7.83 GB, ~10.5 GB memory at 8k context).
What GPU do you need for Qwen3.8 27B Artemis?
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 Q4_0 (1.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (1.3 GB file, about 4.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (1.3 GB file, about 4.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (7.8 GB file, about 10.5 GB in use).
Which Qwen3.8 27B Artemis quant should you choose?
Q4_0 (1.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.8 27B Artemis
How much VRAM does Qwen3.8 27B Artemis need?
About 4.0 GB at Q4_0 with an 8K context window. That is the 1.3 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 Qwen3.8 27B Artemis on an 8 GB GPU?
Yes, with Q4_0: the 1.3 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.8 27B Artemis GGUF?
It depends on the quant: Q4_0 is 1.3 GB, IQ2_XXS is 7.8 GB.
What context length does Qwen3.8 27B Artemis 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 Qwen3.8 27B Artemis GGUF?
The files are on Hugging Face in the turintech/Qwen3.8-27B-Artemis-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 Qwen3.8 27B Artemis 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 Qwen3.8 27B Artemis on 8 GB VRAM?
Yes, with the Q4_0 quant file it requires about 4 GB GPU memory at 8k context.
Does it support vision without extra files?
No, vision requires the optional projector file; text only can be run with --no-mmproj.
What llama.cpp version is needed?
Text requires llama.cpp b11617 or newer; the projector and MTP file were tested on b11889.