PO

Poro 34B chat i1

PoroGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters35.1B
Context7K
Layers54
Architecturebloom
Smallest quant7.8 GB
Quick answer

Poro 34B chat i1 needs about 35.6 GB of memory at Q4_K_M (a 22.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 7.8 GB (IQ1_S) to 28.8 GB (Q6_K).

Poro 34B chat, a Finnish‑English instruction‑tuned LLM

Poro 34B chat is a chat‑tuned version of the 35.1B Poro model. It follows instructions in Finnish and English and can translate between the two languages. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following in Finnish and English
  • Basic translation between Finnish and English
  • ChatML template support

Limits

  • Requires 8k context length
  • No vision support
  • Apache‑2.0 license

Best for

  • Chatbots needing Finnish support
  • Translation assistance
  • Instruction‑driven applications

Who it’s for. Developers building multilingual chat interfaces or translation tools that require a Finnish‑English model. Researchers exploring low‑resource language LLMs may also find it useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.8 GB 19.4 GB
Too big Get file →
IQ1_M8.5 GB 20.1 GB
Too big Get file →
IQ2_XXS9.6 GB 21.2 GB
Too big Get file →
IQ2_XS10.6 GB 22.2 GB
Too big Get file →
IQ2_S11.2 GB 22.8 GB
Too big Get file →
IQ2_M12.2 GB 23.8 GB
Too big Get file →
Q2_K13.4 GB 25.0 GB
Too big Get file →
IQ3_XXS13.9 GB 25.5 GB
Too big Get file →
IQ3_XS15.1 GB 26.7 GB
Too big Get file →
IQ3_S15.5 GB 27.1 GB
Too big Get file →
Q3_K_S15.5 GB 27.1 GB
Too big Get file →
IQ3_M17.1 GB 28.7 GB
Too big Get file →
Q3_K_M18.5 GB 30.1 GB
Too big Get file →
IQ4_XS19.0 GB 30.6 GB
Too big Get file →
Q4_020.1 GB 31.7 GB
Too big Get file →
Q3_K_L20.2 GB 31.8 GB
Too big Get file →
Q4_K_S20.2 GB 31.8 GB
Too big Get file →
Q4_K_M22.4 GB 34.0 GB
Too big Get file →
Q5_K_S24.3 GB 35.9 GB
Too big Get file →
Q5_K_M26.1 GB 37.7 GB
Too big Get file →
Q6_K28.8 GB 40.4 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (7.8 GB file, 21 GB memory). With 12 GB VRAM IQ2_XS (10.63 GB file, 23.8 GB memory) is suitable. For 24 GB VRAM Q4_K_M (22.44 GB file, 35.6 GB memory) offers higher quality.

What GPU do you need for Poro 34B chat 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: 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: the best quant that fits is IQ2_XS (10.6 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (18.5 GB file, about 31.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (28.8 GB file, about 42.0 GB in use).

Which Poro 34B chat i1 quant should you choose?

Q4_K_M is the usual starting point for Poro 34B chat i1: it balances file size and quality well. Here it is a 22.4 GB file.

If memory is tight, the smallest file is IQ1_S at 7.8 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

Architecturebloom
Parameters35.1B
Layers54
Trained context7,168 tokens
KV cache (fp16)1512 KB per token

Source

Quantized bymradermacher
FamilyPoro
Licenseapache-2.0
Downloads (HF)1,669
Last updated2024-08-02

Frequently asked questions about Poro 34B chat i1

How much VRAM does Poro 34B chat i1 need?

About 35.6 GB at Q4_K_M with an 8K context window. That is the 22.4 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 Poro 34B chat i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Poro 34B chat i1 GGUF?

It depends on the quant: IQ1_S is 7.8 GB, IQ1_M is 8.5 GB, IQ2_XXS is 9.6 GB, IQ2_XS is 10.6 GB, IQ2_S is 11.2 GB, IQ2_M is 12.2 GB and 15 more.

What context length does Poro 34B chat i1 support?

The GGUF header lists a trained context length of 7,168 tokens (7K). The KV cache grows with the context you use: about 12.7 GB at 8K and 11.1 GB at 7K.

Where can I download Poro 34B chat i1 GGUF?

The files are on Hugging Face in the mradermacher/Poro-34B-chat-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 Poro 34B chat i1 use?

Hugging Face lists the license as apache-2.0. 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 Poro 34B chat on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 21 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Poro-34B-chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Poro models

All Poro →

Other large models

All large models →