KY

Kyllima 34B v1 i1

KyllimaGGUF by mradermacherUpdated 2025-02-03
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant7.5 GB
Quick answer

Kyllima 34B v1 i1 needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.5 GB (IQ1_S) to 28.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Kyllima 34B v1 i1 – 34.4B parameter Llama model with 200k context

Kyllima 34B v1 i1 is a 34.4B parameter Llama model merged from two Yi 34B-based models. It supports 200000 context tokens and is uncensored. The model is available in multiple GGUF quantizations.

Good at

  • Creative writing
  • Roleplay
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Apache‑2.0 license

Best for

  • Chatbots needing long context
  • Story generation
  • Text analysis

Who it’s for. Developers and researchers who need a large Llama model with extended context. The model is suitable for applications that can handle the memory requirements of a 34B parameter model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.5 GB 10.0 GB
Too big Get file →
IQ1_M8.2 GB 10.7 GB
Too big Get file →
IQ2_XXS9.3 GB 11.8 GB
Too big Get file →
IQ2_XS10.3 GB 12.8 GB
Too big Get file →
IQ2_S10.9 GB 13.4 GB
Too big Get file →
IQ2_M11.8 GB 14.3 GB
Too big Get file →
Q2_K_S11.9 GB 14.4 GB
Too big Get file →
Q2_K12.8 GB 15.3 GB
Too big Get file →
IQ3_XXS13.3 GB 15.8 GB
Too big Get file →
IQ3_XS14.2 GB 16.7 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
IQ3_S15.0 GB 17.5 GB
Too big Get file →
IQ3_M15.6 GB 18.1 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
IQ4_XS18.5 GB 21.0 GB
Too big Get file →
Q4_019.5 GB 22.0 GB
Too big Get file →
Q4_K_S19.6 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q4_121.6 GB 24.1 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →

For 8‑12 GB VRAM, use IQ1_S (7.5 GB) or IQ1_M (8.18 GB). For 12‑16 GB VRAM, IQ2_XS (10.31 GB) or IQ2_S (10.89 GB) are suitable. For 16‑24 GB VRAM, consider Q3_K_S (14.96 GB) or Q4_K_S (19.6 GB). Memory estimates are approximate.

What GPU do you need for Kyllima 34B v1 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: the best quant that fits is IQ2_XXS (9.3 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.3 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).

Which Kyllima 34B v1 i1 quant should you choose?

Q4_K_M is the usual starting point for Kyllima 34B v1 i1: it balances file size and quality well. Here it is a 20.7 GB file.

If memory is tight, the smallest file is IQ1_S at 7.5 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
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymradermacher
FamilyKyllima
Licenseapache-2.0
Downloads (HF)678
Last updated2025-02-03

Frequently asked questions about Kyllima 34B v1 i1

How much VRAM does Kyllima 34B v1 i1 need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 Kyllima 34B v1 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kyllima 34B v1 i1 GGUF?

It depends on the quant: IQ1_S is 7.5 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, IQ2_S is 10.9 GB, IQ2_M is 11.8 GB and 17 more.

What context length does Kyllima 34B v1 i1 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Kyllima 34B v1 i1 GGUF?

The files are on Hugging Face in the mradermacher/Kyllima-34B-v1-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 Kyllima 34B v1 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 this model on 8 GB VRAM?

Use the IQ1_S or IQ1_M quant, which are 7.5 GB and 8.18 GB respectively, with an estimated 10 GB VRAM usage at 8k context.

Does this model support image input?

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 Kyllima-34B-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kyllima models

All Kyllima →

Other large models

All large models →