ST

strix rufipes 70b

StrixGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

strix rufipes 70b needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

Strix Rufipes 70B – a 70B‑parameter Llama‑based model fine‑tuned for logic enforcement

Strix Rufipes 70B is a 69‑billion‑parameter auto‑regressive language model built on the Llama 2 architecture. It is fine‑tuned for logic enforcement and planning tasks. The model is available in multiple GGUF quantizations.

Good at

  • Logic enforcement
  • Planning exercises
  • English language generation

Limits

  • No vision support
  • License is llama2
  • Context length limited to 4096 tokens

Best for

  • Automated planning scripts
  • Logic‑driven dialogue systems
  • Complex reasoning tasks

Who it’s for. Developers and researchers who need a large language model with a focus on logical consistency and planning. The model is suitable for applications that require detailed reasoning in English.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
IQ4_XS37.2 GB 39.0 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For a 8 GB VRAM setup, the smallest quantization is Q2_K with a file size of 25.46 GB and an estimated memory of 28.6 GB at 8 k context. This still exceeds 8 GB VRAM, so the model cannot run on such hardware. For larger GPUs, Q4_K_M (41.42 GB, 44.6 GB memory) or Q5_K_M (48.75 GB, 51.9 GB memory) are recommended for better quality. The estimates are approximate.

What GPU do you need for strix rufipes 70b?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which strix rufipes 70b quant should you choose?

Q4_K_M is the usual starting point for strix rufipes 70b: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyStrix
Licensellama2
Downloads (HF)1,132
Last updated2024-05-06

Frequently asked questions about strix rufipes 70b

How much VRAM does strix rufipes 70b need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 strix rufipes 70b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of strix rufipes 70b GGUF?

It depends on the quant: Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB, Q3_K_M is 33.3 GB and 6 more.

What context length does strix rufipes 70b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download strix rufipes 70b GGUF?

The files are on Hugging Face in the mradermacher/strix-rufipes-70b-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 strix rufipes 70b use?

Hugging Face lists the license as llama2. 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 Strix Rufipes 70B on 8 GB VRAM?

No. Even the smallest quantization requires more than 28 GB of VRAM at 8 k context.

What is the maximum context length?

The model supports up to 4096 tokens.

Is the model licensed for commercial use?

It is licensed under llama2, which allows commercial use under its terms.

Other GGUFs of strix-rufipes-70b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Strix models

All Strix →

Other large models

All large models →