AV

Avenger2.01-xb-Passthrough

AvengerGGUF by mradermacherUpdated 2024-06-08
Download on Hugging Face
Parameters12.3B
Context32K
Layers55
Architecturellama
Smallest quant4.6 GB
Quick answer

Avenger2.01-xb-Passthrough needs about 9.7 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.6 GB (Q2_K) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.4 GB.

12.3B llama model with 32k context

Avenger2.01-xb-Passthrough is a 12.3 billion parameter llama architecture model. It supports a 32768 token context window and is available in multiple GGUF quantizations. The model is provided by mradermacher and has no explicit license listed.

Good at

  • Large context handling
  • Versatile quant options
  • High parameter count

Limits

  • No license specified
  • No vision support
  • Requires large VRAM for higher quants

Best for

  • Chat applications needing long context
  • Fine‑tuning with limited GPU memory
  • Research on llama architecture

Who it’s for. Developers and researchers who need a 12.3B llama model with a 32k context window and are comfortable selecting from a range of quantizations. The model is suitable for those who can manage the memory requirements of the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.6 GB 6.9 GB
Fits Get file →
IQ3_XS5.1 GB 7.4 GB
Tight Get file →
Q3_K_S5.3 GB 7.7 GB
Tight Get file →
IQ3_S5.4 GB 7.7 GB
Tight Get file →
IQ3_M5.5 GB 7.9 GB
Tight Get file →
Q3_K_M5.9 GB 8.3 GB
Too big Get file →
Q3_K_L6.5 GB 8.8 GB
Too big Get file →
IQ4_XS6.6 GB 9.0 GB
Too big Get file →
Q4_K_S7.0 GB 9.3 GB
Too big Get file →
Q4_K_M7.4 GB 9.7 GB
Too big Get file →
Q5_K_S8.4 GB 10.8 GB
Too big Get file →
Q5_K_M8.7 GB 11.0 GB
Too big Get file →
Q6_K10.1 GB 12.4 GB
Too big Get file →
Q8_013.0 GB 15.4 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.56 GB, 6.9 GB memory) or IQ3_XS (5.07 GB, 7.4 GB memory). With 12 GB VRAM, Q4_K_M (7.37 GB, 9.7 GB memory) or Q5_K_S (8.45 GB, 10.8 GB memory) are suitable. Higher quants like Q8_0 require 13.03 GB and 15.4 GB memory, so they need more VRAM.

What GPU do you need for Avenger2.01-xb-Passthrough?

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: the best quant that fits is IQ3_M (5.5 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.7 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 15.4 GB in use).

Which Avenger2.01-xb-Passthrough quant should you choose?

Q4_K_M is the usual starting point for Avenger2.01-xb-Passthrough: it balances file size and quality well. Here it is a 7.4 GB file.

The Q8_0 file is 13.0 GB, about 1.8 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 Q2_K at 4.6 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

Architecturellama
Parameters12.3B
Layers55
Trained context32,768 tokens
KV cache (fp16)220 KB per token

Source

Quantized bymradermacher
FamilyAvenger
Downloads (HF)1,705
Last updated2024-06-08

Frequently asked questions about Avenger2.01-xb-Passthrough

How much VRAM does Avenger2.01-xb-Passthrough need?

About 9.7 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Avenger2.01-xb-Passthrough on an 8 GB GPU?

Yes, with IQ3_M: the 5.5 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Avenger2.01-xb-Passthrough GGUF?

It depends on the quant: Q2_K is 4.6 GB, IQ3_XS is 5.1 GB, Q3_K_S is 5.3 GB, IQ3_S is 5.4 GB, IQ3_M is 5.5 GB, Q3_K_M is 5.9 GB and 8 more.

What context length does Avenger2.01-xb-Passthrough support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.4 GB at 32K.

Where can I download Avenger2.01-xb-Passthrough GGUF?

The files are on Hugging Face in the mradermacher/Avenger2.01-xb-Passthrough-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, using Q2_K or IQ3_XS quantizations, which estimate 6.9–7.4 GB memory at 8k context.

What is the maximum context length?

The model supports 32768 tokens as its trained context length.

Is there a license for this model?

No license information is provided in the model card.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Avenger models

All Avenger →

Other medium models

All medium models →