MI

Roci Maxx v2

MistralGGUF by QuantFactoryUpdated 2024-09-17
Download on Hugging Face
Parameters10.3B
Context1000K
Layers33
Architecturellama
Smallest quant4.1 GB
Quick answer

Roci Maxx v2 needs about 7.9 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 4.1 GB (Q2_K) to 11.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Roci Maxx v2 – 10.3B parameter Mistral model in GGUF format

Roci Maxx v2 is a 10.3B parameter Mistral model merged from TheDrummer/Rocinante-12B-v1.1 and ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1. It is available in multiple GGUF quantizations and supports a context length of 1024000 tokens.

Good at

  • Creative role‑play dialogue
  • Long‑form text generation
  • Low‑repetition responses

Limits

  • No vision support
  • License not specified
  • Large context requires high VRAM

Best for

  • Chatbot development
  • Story writing
  • Interactive fiction

Who it’s for. Developers and researchers who need a large Mistral‑based model for creative text generation and want to run it locally with llama.cpp. The model is suitable for users with sufficient GPU memory to handle the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.1 GB 5.7 GB
Fits Get file →
Q3_K_S4.7 GB 6.3 GB
Fits Get file →
Q3_K_M5.2 GB 6.8 GB
Fits Get file →
Q3_K_L5.6 GB 7.2 GB
Fits Get file →
Q4_06.0 GB 7.6 GB
Tight Get file →
Q4_K_S6.0 GB 7.6 GB
Tight Get file →
Q4_K_M6.3 GB 7.9 GB
Tight Get file →
Q4_16.6 GB 8.2 GB
Too big Get file →
Q5_07.2 GB 8.8 GB
Too big Get file →
Q5_K_S7.2 GB 8.8 GB
Too big Get file →
Q5_K_M7.4 GB 9.0 GB
Too big Get file →
Q5_17.8 GB 9.4 GB
Too big Get file →
Q6_K8.5 GB 10.1 GB
Too big Get file →
Q8_011.0 GB 12.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 6.34 GB, estimated 7.9 GB memory). For 12 GB VRAM, Q5_K_M (7.38 GB, 9 GB memory) or Q6_K (8.49 GB, 10.1 GB memory) are suitable. Higher quants like Q8_0 require 12.6 GB memory and 10.99 GB file size.

What GPU do you need for Roci Maxx v2?

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 Q2_K (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (6.3 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.0 GB file, about 12.6 GB in use).

Which Roci Maxx v2 quant should you choose?

Q4_K_M is the usual starting point for Roci Maxx v2: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 11.0 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 Q2_K at 4.1 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
Parameters10.3B
Layers33
Trained context1,024,000 tokens
KV cache (fp16)132 KB per token

Source

Quantized byQuantFactory
FamilyMistral
Downloads (HF)388
Last updated2024-09-17

Frequently asked questions about Roci Maxx v2

How much VRAM does Roci Maxx v2 need?

About 7.9 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 Roci Maxx v2 on an 8 GB GPU?

Yes, with Q4_K_M: the 6.3 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 Roci Maxx v2 GGUF?

It depends on the quant: Q2_K is 4.1 GB, Q3_K_S is 4.7 GB, Q3_K_M is 5.2 GB, Q3_K_L is 5.6 GB, Q4_0 is 6.0 GB, Q4_K_S is 6.0 GB and 8 more.

What context length does Roci Maxx v2 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Roci Maxx v2 GGUF?

The files are on Hugging Face in the QuantFactory/Roci_Maxx_v2-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 Roci Maxx v2 on 8 GB VRAM?

Yes, using the Q4_K_M quantization which estimates 7.9 GB VRAM usage at 8k context.

What context length does the model support?

The model was trained with a context length of 1024000 tokens.

Does the model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Mistral-Nemo-12B-ArliAI-RPMax-v1.1

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Mistral models

All Mistral →

Other medium models

All medium models →