PS

PsyfighterTwo-ErebusThree-SlerpThree

PsyfightertwoGGUF by mradermacherUpdated 2024-05-30
Download on Hugging Face
Parameters10.5B
Context4K
Layers32
Architecturellama
Smallest quant3.9 GB
Quick answer

PsyfighterTwo-ErebusThree-SlerpThree needs about 12.2 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 3.9 GB (Q2_K) to 11.1 GB (Q8_0).

10.5B‑parameter Llama model merged with SLERP

PsyfighterTwo‑ErebusThree‑SlerpThree is a 10.5B‑parameter Llama model merged from two pre‑trained models using the SLERP merge method. It supports a 4096‑token context window and is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Efficient inference with low‑bit quants
  • Stable merge of two Llama variants

Limits

  • No vision support
  • License not specified
  • Requires 8k context for memory estimates

Best for

  • Chatbot back‑ends
  • Text generation pipelines
  • Research prototyping

Who it’s for. Developers and researchers needing a high‑capacity Llama model with flexible quantization options. The model is suitable for local deployment on machines with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.9 GB 7.1 GB
Fits Get file →
IQ3_XS4.3 GB 7.5 GB
Tight Get file →
IQ3_S4.6 GB 7.8 GB
Tight Get file →
Q3_K_S4.6 GB 7.8 GB
Tight Get file →
IQ3_M4.8 GB 8.0 GB
Too big Get file →
Q3_K_M5.1 GB 8.3 GB
Too big Get file →
Q3_K_L5.6 GB 8.8 GB
Too big Get file →
IQ4_XS5.7 GB 8.8 GB
Too big Get file →
Q4_K_S6.0 GB 9.2 GB
Too big Get file →
Q4_K_M6.3 GB 9.5 GB
Too big Get file →
Q5_K_S7.2 GB 10.4 GB
Too big Get file →
Q5_K_M7.4 GB 10.6 GB
Too big Get file →
Q6_K8.6 GB 11.8 GB
Too big Get file →
Q8_011.1 GB 14.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 3.92 GB, estimated 9.8 GB memory). For 12 GB VRAM, Q4_K_M (file size 6.34 GB, estimated 12.2 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (file size 7.43 GB, estimated 13.3 GB memory) provides higher quality.

What GPU do you need for PsyfighterTwo-ErebusThree-SlerpThree?

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: the best quant that fits is Q4_K_S (6.0 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (8.6 GB file, about 14.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (11.1 GB file, about 17.0 GB in use).

Which PsyfighterTwo-ErebusThree-SlerpThree quant should you choose?

Q4_K_M is the usual starting point for PsyfighterTwo-ErebusThree-SlerpThree: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 11.1 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 3.9 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
Parameters10.5B
Layers32
Trained context4,096 tokens
KV cache (fp16)640 KB per token

Source

Quantized bymradermacher
Downloads (HF)1,602
Last updated2024-05-30

Frequently asked questions about PsyfighterTwo-ErebusThree-SlerpThree

How much VRAM does PsyfighterTwo-ErebusThree-SlerpThree need?

About 12.2 GB at Q4_K_M with an 8K context window. That is the 6.3 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 PsyfighterTwo-ErebusThree-SlerpThree on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PsyfighterTwo-ErebusThree-SlerpThree GGUF?

It depends on the quant: Q2_K is 3.9 GB, IQ3_XS is 4.3 GB, IQ3_S is 4.6 GB, Q3_K_S is 4.6 GB, IQ3_M is 4.8 GB, Q3_K_M is 5.1 GB and 8 more.

What context length does PsyfighterTwo-ErebusThree-SlerpThree support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 5.4 GB at 8K and 2.7 GB at 4K.

Where can I download PsyfighterTwo-ErebusThree-SlerpThree GGUF?

The files are on Hugging Face in the mradermacher/PsyfighterTwo-ErebusThree-SlerpThree-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, the Q2_K quant requires about 9.8 GB memory at 8k context, which fits within 8 GB VRAM with some overhead.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the context length?

The model supports a 4096‑token context window.

Other GGUFs of PsyfighterTwo-ErebusThree-SlerpThree

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Psyfightertwo models

All Psyfightertwo →

Other medium models

All medium models →