RO

Roci Maxx i1

RociGGUF by mradermacherUpdated 2024-09-15
Download on Hugging Face
Parameters10.1B
Context1000K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

Roci Maxx i1 needs about 7.7 GB of memory at Q4_K_M (a 6.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.5 GB (IQ1_S) to 8.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

10.1B‑parameter Roci model with tool‑use capability

Roci Maxx i1 is a 10.1B‑parameter language model merged from Mistral‑Nemo and Rocinante. It supports tool use and a context length of 1,024,000 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Tool use
  • Large context
  • 10.1B parameters

Limits

  • No vision support
  • No license specified
  • Large VRAM requirement

Best for

  • Tool‑enabled chatbots
  • Long‑form content generation
  • Context‑heavy data analysis

Who it’s for. Developers building applications that need tool integration and long‑context reasoning. The model is suitable for users with sufficient GPU memory to load the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.5 GB 4.1 GB
Fits Get file →
IQ1_M2.7 GB 4.3 GB
Fits Get file →
IQ2_XXS3.0 GB 4.6 GB
Fits Get file →
IQ2_XS3.3 GB 4.8 GB
Fits Get file →
IQ2_S3.5 GB 5.0 GB
Fits Get file →
IQ2_M3.7 GB 5.3 GB
Fits Get file →
Q2_K4.0 GB 5.6 GB
Fits Get file →
IQ3_XXS4.1 GB 5.7 GB
Fits Get file →
IQ3_XS4.4 GB 6.0 GB
Fits Get file →
Q3_K_S4.6 GB 6.2 GB
Fits Get file →
IQ3_S4.6 GB 6.2 GB
Fits Get file →
IQ3_M4.7 GB 6.3 GB
Fits Get file →
Q3_K_M5.0 GB 6.6 GB
Fits Get file →
Q3_K_L5.4 GB 7.0 GB
Fits Get file →
IQ4_XS5.6 GB 7.2 GB
Fits Get file →
Q4_05.8 GB 7.4 GB
Tight Get file →
Q4_05.8 GB 7.4 GB
Tight Get file →
Q4_05.8 GB 7.4 GB
Tight Get file →
Q4_05.9 GB 7.4 GB
Tight Get file →
Q4_K_S5.9 GB 7.5 GB
Tight Get file →
Q4_K_M6.2 GB 7.7 GB
Tight Get file →
Q5_K_S7.0 GB 8.6 GB
Too big Get file →
Q5_K_M7.2 GB 8.8 GB
Too big Get file →
Q6_K8.3 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.54 GB, memory 4.1 GB) or IQ1_M (2.72 GB, 4.3 GB). For 12 GB VRAM, IQ2_S (3.46 GB, 5 GB) or Q2_K (3.99 GB, 5.6 GB) are suitable. Higher‑quality quants such as Q5_K_M (7.19 GB, 8.8 GB) require 16 GB or more.

What GPU do you need for Roci Maxx i1?

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 IQ3_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (6.2 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.3 GB file, about 9.8 GB in use).

Which Roci Maxx i1 quant should you choose?

Q4_K_M is the usual starting point for Roci Maxx i1: it balances file size and quality well. Here it is a 6.2 GB file.

If memory is tight, the smallest file is IQ1_S at 2.5 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
Parameters10.1B
Layers32
Trained context1,024,000 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyRoci
Downloads (HF)671
Last updated2024-09-15

Frequently asked questions about Roci Maxx i1

How much VRAM does Roci Maxx i1 need?

About 7.7 GB at Q4_K_M with an 8K context window. That is the 6.2 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 i1 on an 8 GB GPU?

Yes, with Q4_K_M: the 6.2 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Roci Maxx i1 GGUF?

It depends on the quant: IQ1_S is 2.5 GB, IQ1_M is 2.7 GB, IQ2_XXS is 3.0 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.5 GB, IQ2_M is 3.7 GB and 18 more.

What context length does Roci Maxx i1 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 4.3 GB at 32K.

Where can I download Roci Maxx i1 GGUF?

The files are on Hugging Face in the mradermacher/Roci-Maxx-i1-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 i1 on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quants, which use about 4.1–4.3 GB of VRAM at 8 k context.

Does the model support vision?

No, the model has no vision capability.

What is the maximum context length?

The model supports up to 1,024,000 tokens of context.

Other GGUFs of Roci-Maxx

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Roci models

All Roci →

Other medium models

All medium models →