QW

Tess-v2.5.2-Qwen2-72B

QwenGGUF by mradermacherUpdated 2024-06-15
Download on Hugging Face
Parameters72.7B
Context128K
Layers80
Architectureqwen2
Smallest quant29.8 GB
Quick answer

Tess-v2.5.2-Qwen2-72B needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 29.8 GB (Q2_K) to 47.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Tess‑v2.5.2‑Qwen2‑72B – a 72.7B‑parameter LLM fine‑tuned for conversation

Tess‑v2.5.2‑Qwen2‑72B is a 72.7B‑parameter model based on Qwen2 architecture. It is fine‑tuned from Qwen2‑72B with a subset of the Tess‑v2.5 dataset. The model is designed to generate natural conversations and handle follow‑up questions.

Good at

  • Natural dialogue generation
  • Follow‑up question handling
  • Reasoning and coding tasks

Limits

  • No vision support
  • Requires large VRAM for high‑quality quants
  • License is other

Best for

  • Chatbot development
  • Interactive QA systems
  • Coding assistance

Who it’s for. Developers building conversational agents or coding assistants who need a large language model with natural dialogue flow. The model is suitable for users with sufficient GPU memory to run high‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.8 GB 33.0 GB
Too big Get file →
IQ3_XS32.8 GB 36.0 GB
Too big Get file →
IQ3_S34.5 GB 37.7 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
IQ3_M35.5 GB 38.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_L39.5 GB 42.7 GB
Too big Get file →
IQ4_XS40.2 GB 43.3 GB
Too big Get file →
Q4_K_S43.9 GB 47.1 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 29.81 GB, estimated 33 GB memory at 8 k context). For 12 GB VRAM, IQ3_XS (32.84 GB, 36 GB memory) or Q3_K_S (34.49 GB, 37.7 GB memory). For 16 GB VRAM, Q4_K_S (43.89 GB, 47.1 GB memory) or Q4_K_M (47.42 GB, 50.6 GB memory) are suitable. Memory estimates are approximate.

What GPU do you need for Tess-v2.5.2-Qwen2-72B?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).

Which Tess-v2.5.2-Qwen2-72B quant should you choose?

Q4_K_M is the usual starting point for Tess-v2.5.2-Qwen2-72B: it balances file size and quality well. Here it is a 47.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.8 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

Architectureqwen2
Parameters72.7B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)543
Last updated2024-06-15

Frequently asked questions about Tess-v2.5.2-Qwen2-72B

How much VRAM does Tess-v2.5.2-Qwen2-72B need?

About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 Tess-v2.5.2-Qwen2-72B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tess-v2.5.2-Qwen2-72B GGUF?

It depends on the quant: Q2_K is 29.8 GB, IQ3_XS is 32.8 GB, IQ3_S is 34.5 GB, Q3_K_S is 34.5 GB, IQ3_M is 35.5 GB, Q3_K_M is 37.7 GB and 4 more.

What context length does Tess-v2.5.2-Qwen2-72B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Tess-v2.5.2-Qwen2-72B GGUF?

The files are on Hugging Face in the mradermacher/Tess-v2.5.2-Qwen2-72B-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 Tess-v2.5.2-Qwen2-72B 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 Tess‑v2.5.2‑Qwen2‑72B on 8 GB VRAM?

The Q2_K quant requires about 33 GB memory at 8 k context, so 8 GB VRAM is insufficient. Use a lower‑parameter model instead.

What is the file size of the smallest quant?

The smallest quant is Q2_K with a file size of 29.81 GB.

Does this model support vision tasks?

No, the model does not have vision capabilities.

Other GGUFs of Tess-v2.5.2-Qwen2-72B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →