YI

brucethemoose_yi-34b-200k-dare-megamerge-v8

YiGGUF by TheBlokeUpdated 2024-01-15
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant9.3 GB
Quick answer

brucethemoose_yi-34b-200k-dare-megamerge-v8 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 15 quants, from 9.3 GB (IQ2_XXS) to 36.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Yi 34B 200K DARE MegaMerge V8 – large context, 34 billion parameters

Yi 34B 200K DARE MegaMerge V8 is a 34 billion parameter model merged with DARE Ties. It supports up to 200 000 context tokens and is optimized for large‑context inference. The model is available in multiple GGUF quantizations for llama.cpp and other GGUF‑compatible clients.

Good at

  • Large context inference up to 200 000 tokens
  • High‑quality text generation with Orca‑Vicuna prompt template
  • Efficient use of importance‑matrix quantization

Limits

  • Requires context‑efficient backends for full 200 k context
  • Memory usage high for full precision – 39 GB at 8 k context for Q8_0
  • License is other; check usage terms

Best for

  • Long‑form content creation
  • Research with extended context needs
  • Fine‑tuning on custom datasets with large context

Who it’s for. Developers and researchers needing a 34 billion parameter model that can handle very long contexts. Suitable for local deployment with llama.cpp or compatible GGUF clients.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.3 GB 11.8 GB
Too big Get file →
IQ2_XS10.3 GB 12.8 GB
Too big Get file →
Q2_K_S11.8 GB 14.3 GB
Too big Get file →
Q2_K12.8 GB 15.3 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 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 →
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 →
Q5_023.7 GB 26.2 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 →
Q8_036.5 GB 39.1 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (9.31 GB) or IQ2_XS (10.31 GB). For 16 GB VRAM, Q2_K_S (11.76 GB) or Q3_K_S (14.96 GB) provide a balance of size and quality. For 24 GB VRAM, Q4_K_M (20.66 GB) or Q5_K_M (24.32 GB) give higher fidelity while staying within memory limits. Estimates are approximate.

What GPU do you need for brucethemoose_yi-34b-200k-dare-megamerge-v8?

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 Q2_K (12.8 GB file, about 15.3 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).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which brucethemoose_yi-34b-200k-dare-megamerge-v8 quant should you choose?

Q4_K_M is the usual starting point for brucethemoose_yi-34b-200k-dare-megamerge-v8: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 9.3 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 byTheBloke
FamilyYi
Licenseother
Downloads (HF)7,053
Last updated2024-01-15

Frequently asked questions about brucethemoose_yi-34b-200k-dare-megamerge-v8

How much VRAM does brucethemoose_yi-34b-200k-dare-megamerge-v8 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 brucethemoose_yi-34b-200k-dare-megamerge-v8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of brucethemoose_yi-34b-200k-dare-megamerge-v8 GGUF?

It depends on the quant: IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, Q2_K_S is 11.8 GB, Q2_K is 12.8 GB, Q3_K_S is 15.0 GB, Q3_K_M is 16.7 GB and 9 more.

What context length does brucethemoose_yi-34b-200k-dare-megamerge-v8 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 brucethemoose_yi-34b-200k-dare-megamerge-v8 GGUF?

The files are on Hugging Face in the TheBloke/Yi-34B-200K-DARE-megamerge-v8-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 brucethemoose_yi-34b-200k-dare-megamerge-v8 use?

Hugging Face lists the license as other. 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 Yi‑34B‑200K on a 8 GB GPU?

Use IQ2_XXS or IQ2_XS quantizations; they fit within 8 GB VRAM with about 12–13 GB memory usage at 8 k context.

What context length can I use with this model?

The model was trained with 200 000 tokens; full context requires context‑efficient backends like exllamav2 or unsloth.

Is there a vision capability?

No vision support is included in this model; it is purely text‑based.

Other GGUFs of Yi-34B-200K-DARE-megamerge-v8

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Yi models

All Yi →

Other large models

All large models →