YI

dolphin-2.9.1-yi-1.5-34b

YiGGUF by RichardErkhovUpdated 2024-07-19
Download on Hugging Face
Parameters34.4B
Context8K
Layers60
Architecturellama
Smallest quant12.8 GB
Quick answer

dolphin-2.9.1-yi-1.5-34b 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 22 quants, from 12.8 GB (Q2_K) to 36.5 GB (Q8_0).

Large Yi-based model with 34.4B parameters

dolphin-2.9.1-yi-1.5-34b is a 34.4B parameter model based on the Yi architecture. It supports a 8192 token context window and is available in multiple GGUF quantizations. The model was trained on a diverse set of instruction and coding datasets.

Good at

  • Instruction following
  • Code generation
  • Multitask dialogue

Limits

  • No vision support
  • No license specified
  • Large memory requirement

Best for

  • Chatbot development
  • Code assistance
  • Research prototyping

Who it’s for. Developers and researchers who need a high‑capacity language model for complex instruction following and code generation tasks. The model is suitable for environments that can accommodate its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.8 GB 15.3 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_K16.7 GB 19.2 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_XS18.6 GB 21.1 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 →
IQ4_NL19.7 GB 22.2 GB
Too big Get file →
Q4_K20.7 GB 23.2 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_023.7 GB 26.2 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K24.3 GB 26.8 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q5_125.8 GB 28.3 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 8k context, Q4_K_M uses about 23.2GB of VRAM and is a good balance between size and performance. If more VRAM is available, Q5_K_M (26.8GB) or Q6_K (30.7GB) provide higher quality. For tighter budgets, Q3_K_M (18.1GB) or Q3_K_S (17.5GB) are options.

What GPU do you need for dolphin-2.9.1-yi-1.5-34b?

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: 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 (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 dolphin-2.9.1-yi-1.5-34b quant should you choose?

Q4_K_M is the usual starting point for dolphin-2.9.1-yi-1.5-34b: 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 Q2_K at 12.8 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

Architecturellama
Parameters34.4B
Layers60
Trained context8,192 tokens
KV cache (fp16)240 KB per token

Source

Quantized byRichardErkhov
FamilyYi
Downloads (HF)492
Last updated2024-07-19

Frequently asked questions about dolphin-2.9.1-yi-1.5-34b

How much VRAM does dolphin-2.9.1-yi-1.5-34b 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 dolphin-2.9.1-yi-1.5-34b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dolphin-2.9.1-yi-1.5-34b GGUF?

It depends on the quant: Q2_K is 12.8 GB, IQ3_XS is 14.2 GB, Q3_K_S is 15.0 GB, IQ3_S is 15.0 GB, IQ3_M is 15.6 GB, Q3_K is 16.7 GB and 16 more.

What context length does dolphin-2.9.1-yi-1.5-34b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.0 GB at 8K and 2.0 GB at 8K.

Where can I download dolphin-2.9.1-yi-1.5-34b GGUF?

The files are on Hugging Face in the RichardErkhov/cognitivecomputations_-_dolphin-2.9.1-yi-1.5-34b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

No, the smallest quantization requires at least 15.3GB of VRAM at 8k context. 8 GB VRAM is insufficient.

What is the maximum context length?

The model supports 8192 tokens of context.

Is there a license for using this model?

No license information is provided in the model card.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Yi models

All Yi →

Other large models

All large models →