LL

ArrowCanaria Llama 8B SFT v0.1

LlamaGGUF by mmnga-oUpdated 2026-03-21
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant3.8 GB
Quick answer

ArrowCanaria Llama 8B SFT v0.1 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 3.8 GB (IQ3_M) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Japanese‑focused 8B Llama model for natural chat and role‑play

ArrowCanaria Llama 8B SFT v0.1 is a Japanese‑centric 8.03 billion‑parameter model designed for casual conversation and role‑play. It builds on Llama‑3.1‑Swallow‑8B‑Instruct and adds domain knowledge through synthetic data and curriculum SFT. The model excels in natural dialogue, emotional response, and tool use.

Good at

  • Natural Japanese conversation
  • Role‑play with consistent personality
  • Tool calling and RAG

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • License: llama3.3

Best for

  • AI VTuber chat
  • Chatbot for daily Japanese conversation
  • Creative writing assistance

Who it’s for. Developers building Japanese chatbots or AI VTubers who need natural, emotionally aware dialogue. The model is suitable for applications that require consistent character voice and tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_05.6 GB 7.2 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
MXFP4_MOE8.5 GB 10.1 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

For 8 GB VRAM use IQ3_M (3.78 GB, 5.4 GB memory at 8 k context) or Q3_K_M (4.02 GB, 5.6 GB). With 12 GB VRAM Q4_K_M (4.92 GB, 6.5 GB) is a good balance. For 24 GB VRAM Q5_K_M (5.73 GB, 7.3 GB) or Q6_K (6.6 GB, 8.2 GB) provide higher quality.

What GPU do you need for ArrowCanaria Llama 8B SFT v0.1?

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 IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is MXFP4_MOE (8.5 GB file, about 10.1 GB in use).

Which ArrowCanaria Llama 8B SFT v0.1 quant should you choose?

Q4_K_M is the usual starting point for ArrowCanaria Llama 8B SFT v0.1: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 IQ3_M at 3.8 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymmnga-o
FamilyLlama
Licensellama3.3
Downloads (HF)563
Last updated2026-03-21

Frequently asked questions about ArrowCanaria Llama 8B SFT v0.1

How much VRAM does ArrowCanaria Llama 8B SFT v0.1 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 ArrowCanaria Llama 8B SFT v0.1 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ArrowCanaria Llama 8B SFT v0.1 GGUF?

It depends on the quant: IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, IQ4_XS is 4.4 GB, Q4_0 is 4.7 GB, IQ4_NL is 4.7 GB and 8 more.

What context length does ArrowCanaria Llama 8B SFT v0.1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download ArrowCanaria Llama 8B SFT v0.1 GGUF?

The files are on Hugging Face in the mmnga-o/ArrowCanaria-Llama-8B-SFT-v0.1-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 ArrowCanaria Llama 8B SFT v0.1 use?

Hugging Face lists the license as llama3.3. 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 this model on 8 GB VRAM?

Yes, use IQ3_M or Q3_K_M quantizations; they fit within 8 GB VRAM and use about 5.4–5.6 GB memory at 8 k context.

Does the model support image input?

No, the model has no vision capability.

What context length does it support?

It was trained with 131072 tokens and can run with 8 k context for the provided memory estimates.

Similar models

Browse all →

More from mmnga-o

All by mmnga-o →

More Llama models

All Llama →

Other small models

All small models →