FR

Franqwenstein 35b

FranqwensteinGGUF by mradermacherUpdated 2024-10-04
Download on Hugging Face
Parameters34.7B
Context128K
Layers68
Architectureqwen2
Smallest quant7.7 GB
Quick answer

Franqwenstein 35b needs about 23.8 GB of memory at Q4_K_M (a 21.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.7 GB (IQ1_S) to 28.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.1 GB.

Franqwenstein 35b – a 34.7B Qwen2 model in GGUF format

Franqwenstein 35b is a 34.7B parameter Qwen2 model released under the MIT license. It supports a 131072 token context window and is available in multiple GGUF quantizations. The model combines safety guard from Qwen with AGI finetune obedience.

Good at

  • Large context generation
  • High token throughput
  • Instruction following

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • No mixture of experts

Best for

  • Chatbot development
  • Long‑form content creation
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑context LLM with flexible quantization options. The MIT license allows free use and modification.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.7 GB 10.5 GB
Too big Get file →
IQ1_M8.4 GB 11.2 GB
Too big Get file →
IQ2_XXS9.5 GB 12.3 GB
Too big Get file →
IQ2_XS10.5 GB 13.3 GB
Too big Get file →
IQ2_S11.0 GB 13.8 GB
Too big Get file →
IQ2_M11.9 GB 14.7 GB
Too big Get file →
Q2_K13.0 GB 15.8 GB
Too big Get file →
IQ3_XXS13.6 GB 16.4 GB
Too big Get file →
IQ3_XS14.5 GB 17.3 GB
Too big Get file →
Q3_K_S15.2 GB 18.0 GB
Too big Get file →
IQ3_S15.3 GB 18.1 GB
Too big Get file →
IQ3_M15.7 GB 18.4 GB
Too big Get file →
Q3_K_M16.9 GB 19.6 GB
Too big Get file →
Q3_K_L18.3 GB 21.0 GB
Too big Get file →
IQ4_XS18.7 GB 21.5 GB
Too big Get file →
Q4_019.8 GB 22.6 GB
Too big Get file →
Q4_K_S19.9 GB 22.7 GB
Too big Get file →
Q4_K_M21.0 GB 23.8 GB
Too big Get file →
Q5_K_S24.0 GB 26.8 GB
Too big Get file →
Q5_K_M24.6 GB 27.4 GB
Too big Get file →
Q6_K28.5 GB 31.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.67 GB file, 10.5 GB memory). For 12 GB VRAM, IQ2_XS (10.53 GB file, 13.3 GB memory). For 16 GB VRAM, IQ3_XS (14.5 GB file, 17.3 GB memory). Memory estimates are approximate.

What GPU do you need for Franqwenstein 35b?

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 IQ1_M (8.4 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.0 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.0 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 31.3 GB in use).

Which Franqwenstein 35b quant should you choose?

Q4_K_M is the usual starting point for Franqwenstein 35b: it balances file size and quality well. Here it is a 21.0 GB file.

If memory is tight, the smallest file is IQ1_S at 7.7 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

Architectureqwen2
Parameters34.7B
Layers68
Trained context131,072 tokens
KV cache (fp16)272 KB per token

Source

Quantized bymradermacher
Licensemit
Downloads (HF)1,569
Last updated2024-10-04

Frequently asked questions about Franqwenstein 35b

How much VRAM does Franqwenstein 35b need?

About 23.8 GB at Q4_K_M with an 8K context window. That is the 21.0 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 Franqwenstein 35b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Franqwenstein 35b GGUF?

It depends on the quant: IQ1_S is 7.7 GB, IQ1_M is 8.4 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.5 GB, IQ2_S is 11.0 GB, IQ2_M is 11.9 GB and 15 more.

What context length does Franqwenstein 35b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.1 GB at 32K.

Where can I download Franqwenstein 35b GGUF?

The files are on Hugging Face in the mradermacher/franqwenstein-35b-i1-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 Franqwenstein 35b use?

Hugging Face lists the license as mit. 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 Franqwenstein 35b on 8 GB VRAM?

Yes, the IQ1_S quant uses 7.67 GB file size and requires about 10.5 GB VRAM at 8k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of franqwenstein-35b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Franqwenstein models

All Franqwenstein →

Other large models

All large models →