QW

Einstein-v4-Qwen-1.5-32B

QwenGGUF by mradermacherUpdated 2024-06-16
Download on Hugging Face
Parameters32.5B
Context32K
Layers64
Architectureqwen2
Smallest quant12.2 GB
Quick answer

Einstein-v4-Qwen-1.5-32B needs about 22.3 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 12.2 GB (Q2_K) to 34.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Einstein‑v4‑Qwen‑1.5‑32B – a 32.5B Qwen2 model fine‑tuned for coding and tools

Einstein‑v4‑Qwen‑1.5‑32B is a QLoRA fine‑tuned version of Qwen/Qwen1.5‑32B. It was trained on diverse datasets for 2 epochs with 3352 steps. The model supports a 32768 token context window.

Good at

  • Coding tasks
  • Tool integration
  • Long‑form reasoning

Limits

  • No vision support
  • License type: other
  • Large VRAM requirement

Best for

  • Developers building code assistants
  • Researchers testing large‑context models
  • Teams needing tool‑aware LLMs

Who it’s for. This model is suited for developers and researchers who require a large‑parameter LLM with strong coding and tool‑handling capabilities. It is ideal for environments where a 32.5B parameter model can be run with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.2 GB 14.9 GB
Too big Get file →
IQ3_XS13.6 GB 16.3 GB
Too big Get file →
Q3_K_S14.3 GB 16.9 GB
Too big Get file →
IQ3_S14.3 GB 17.0 GB
Too big Get file →
IQ3_M14.7 GB 17.3 GB
Too big Get file →
Q3_K_M15.8 GB 18.5 GB
Too big Get file →
Q3_K_L17.1 GB 19.8 GB
Too big Get file →
IQ4_XS17.7 GB 20.4 GB
Too big Get file →
Q4_K_S18.6 GB 21.3 GB
Too big Get file →
Q4_K_M19.7 GB 22.3 GB
Too big Get file →
Q5_K_S22.5 GB 25.1 GB
Too big Get file →
Q5_K_M23.1 GB 25.7 GB
Too big Get file →
Q6_K26.7 GB 29.3 GB
Too big Get file →
Q8_034.6 GB 37.2 GB
Too big Get file →

For 8 GB VRAM use Q2_K (12.22 GB file, ~14.9 GB memory). For 12 GB VRAM use Q3_K_S (14.28 GB file, ~16.9 GB memory). For 16 GB VRAM use Q4_K_M (19.7 GB file, ~22.3 GB memory). Estimates are approximate.

What GPU do you need for Einstein-v4-Qwen-1.5-32B?

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 (12.2 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.7 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 29.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.6 GB file, about 37.2 GB in use).

Which Einstein-v4-Qwen-1.5-32B quant should you choose?

Q4_K_M is the usual starting point for Einstein-v4-Qwen-1.5-32B: it balances file size and quality well. Here it is a 19.7 GB file.

The Q8_0 file is 34.6 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 12.2 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
Parameters32.5B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)714
Last updated2024-06-16

Frequently asked questions about Einstein-v4-Qwen-1.5-32B

How much VRAM does Einstein-v4-Qwen-1.5-32B need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 19.7 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 Einstein-v4-Qwen-1.5-32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Einstein-v4-Qwen-1.5-32B GGUF?

It depends on the quant: Q2_K is 12.2 GB, IQ3_XS is 13.6 GB, Q3_K_S is 14.3 GB, IQ3_S is 14.3 GB, IQ3_M is 14.7 GB, Q3_K_M is 15.8 GB and 8 more.

What context length does Einstein-v4-Qwen-1.5-32B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Einstein-v4-Qwen-1.5-32B GGUF?

The files are on Hugging Face in the mradermacher/Einstein-v4-Qwen-1.5-32B-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 Einstein-v4-Qwen-1.5-32B 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 this model on 8 GB VRAM?

Yes, the Q2_K quant uses 12.22 GB file size and requires about 14.9 GB memory at 8k context, which fits 8 GB VRAM with efficient batching.

Does this model support vision tasks?

No, the model has no vision capability. It is designed for text and coding tasks only.

What is the context length of this model?

The model supports a 32768 token context window, allowing for very long inputs.

Other GGUFs of Einstein-v4-Qwen-1.5-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →