GR

GRaPE 2.5 Quasar Q3 K M

GrapeGGUF by DedeProGamesUpdated 2026-09-09
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant13.5 GB
Quick answer

GRaPE 2.5 Quasar Q3 K M needs about 16.2 GB of memory at Q3_K_M (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

GRaPE 2.5 Quasar Q3 K M – multimodal reasoning LLM

GRaPE 2.5 Quasar Q3 K M is a 27.3 billion‑parameter model built on the qwen35 architecture. It supports image, video and text inputs and outputs text. The model is trained for reasoning, roleplay, tools and vision tasks.

Good at

  • Multimodal reasoning
  • Agentic coding
  • Creative text generation

Limits

  • No vision output
  • Requires 16.2 GB VRAM at 8 k context
  • Apache‑2.0 license

Best for

  • Chatbots needing multimodal input
  • Agentic task automation
  • Creative writing assistance

Who it’s for. Developers and researchers who need a versatile multimodal LLM with controllable reasoning depth. The model is suitable for building agents that process images and text together.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M13.5 GB 16.2 GB
Too big Get file →

The Q3_K_M quantization produces a 13.5 GB file and needs about 16.2 GB VRAM at 8 k context. For 8 GB VRAM use a smaller quant if available; otherwise the model cannot run. For 16 GB VRAM the Q3_K_M is suitable.

What GPU do you need for GRaPE 2.5 Quasar Q3 K M?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q3_K_M (13.5 GB file, about 16.2 GB in use).

Which GRaPE 2.5 Quasar Q3 K M quant should you choose?

Q3_K_M (13.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters27.3B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byDedeProGames
FamilyGrape
Licenseapache-2.0
Downloads (HF)757
Last updated2026-09-09

Frequently asked questions about GRaPE 2.5 Quasar Q3 K M

How much VRAM does GRaPE 2.5 Quasar Q3 K M need?

About 16.2 GB at Q3_K_M with an 8K context window. That is the 13.5 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 GRaPE 2.5 Quasar Q3 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GRaPE 2.5 Quasar Q3 K M GGUF?

It depends on the quant: Q3_K_M is 13.5 GB.

What context length does GRaPE 2.5 Quasar Q3 K M 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 GRaPE 2.5 Quasar Q3 K M GGUF?

The files are on Hugging Face in the DedeProGames/GRaPE-2.5-Quasar-Q3_K_M-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 GRaPE 2.5 Quasar Q3 K M 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 GRaPE 2.5 Quasar Q3 K M on 8 GB VRAM?

No. The Q3_K_M quant requires approximately 16.2 GB VRAM at 8 k context.

What is the context length of this model?

The model was trained with 262,144 tokens of context.

Does this model support vision output?

No, it only accepts image, video and text inputs and produces text output.

Other GGUFs of GRaPE-2.5-Quasar

Similar models

Browse all →

More from DedeProGames

All by DedeProGames →

More Grape models

All Grape →

Other medium models

All medium models →