CA

Carnice-V2-27B

CarniceGGUF by kai-osUpdated 2026-04-25
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant10.0 GB
Quick answer

Carnice-V2-27B needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 10.0 GB (IQ2_M) to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Carnice-V2-27B – a 27B Qwen3.5 model optimized for Hermes agent use

Carnice-V2-27B is a 27‑billion‑parameter Qwen3.5 model merged in BF16 and quantized to GGUF. It supports tool usage and is designed for agentic Hermes‑style workflows. The model is released under Apache‑2.0 and has a 262,144‑token context window.

Good at

  • Tool‑based agent interactions
  • Long‑context reasoning up to 262k tokens
  • Hermes‑style agent traces

Limits

  • Large VRAM requirement for higher quants
  • No vision capabilities
  • Requires recent llama.cpp for qwen35 support

Best for

  • Building custom Hermes agents
  • Long‑form dialogue systems
  • Complex tool‑driven tasks

Who it’s for. Developers building agentic applications that need extended context and tool usage. The model is suitable for those who can allocate sufficient GPU memory and run a recent llama.cpp build.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M10.0 GB 12.7 GB
Too big Get file →
Q2_K10.7 GB 13.4 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →
BF1653.8 GB 56.5 GB
Too big Get file →

For 16 GB VRAM, use IQ2_M (10 GB file, ~12.7 GB memory at 8 k context). If IQ quants are unsupported, Q2_K (10.71 GB file, ~13.4 GB memory) is the next best. Higher quants like Q4_K_M or Q5_K_M require 19–21 GB memory and are suitable for 24 GB+ GPUs.

What GPU do you need for Carnice-V2-27B?

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: 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 (10.7 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which Carnice-V2-27B quant should you choose?

Q4_K_M is the usual starting point for Carnice-V2-27B: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 GB, about 1.7 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 IQ2_M at 10.0 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

Architectureqwen35
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bykai-os
FamilyCarnice
Licenseapache-2.0
Downloads (HF)4,962
Last updated2026-04-25

Frequently asked questions about Carnice-V2-27B

How much VRAM does Carnice-V2-27B need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Carnice-V2-27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Carnice-V2-27B GGUF?

It depends on the quant: IQ2_M is 10.0 GB, Q2_K is 10.7 GB, Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, Q8_0 is 28.6 GB, BF16 is 53.8 GB.

What context length does Carnice-V2-27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Carnice-V2-27B GGUF?

The files are on Hugging Face in the kai-os/Carnice-V2-27b-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 Carnice-V2-27B 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 Carnice-V2-27B on 8 GB VRAM?

No. The smallest quant IQ2_M requires ~12.7 GB memory at 8 k context, exceeding 8 GB VRAM.

Does this model support vision?

No, the model has no vision capabilities.

What runtime is needed for this model?

A recent llama.cpp build that supports the qwen35 architecture is required.

Other GGUFs of Carnice-V2-27b

Similar models

Browse all →

More from kai-os

All by kai-os →

More Carnice models

All Carnice →

Other medium models

All medium models →