DE

DeepPulse 80B Thinking V0.1

DeeppulseGGUF by mradermacherUpdated 2026-10-16
Download on Hugging Face
Parameters79.7B
Context256K
Layers48
Architectureqwen3next
Smallest quant29.1 GB
Quick answer

DeepPulse 80B Thinking V0.1 needs about 49.7 GB of memory at Q4_K_M (a 48.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 29.1 GB (Q2_K) to 84.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

DeepPulse 80B Thinking V0.1 – a large TCM reasoning model

DeepPulse 80B Thinking V0.1 is a 79.7 billion‑parameter model fine‑tuned for Traditional Chinese Medicine reasoning. It is based on Qwen3‑Next‑80B and supports complex clinical reasoning and tool usage. The model is released under the Apache‑2.0 license.

Good at

  • TCM clinical reasoning
  • tool‑based inference
  • complex diagnosis

Limits

  • trained context 262144 tokens
  • no vision support
  • requires large VRAM for full precision

Best for

  • TCM clinical decision support
  • TCM exam preparation
  • TCM literature analysis

Who it’s for. Researchers and practitioners in Traditional Chinese Medicine who need a large language model specialized in TCM reasoning. The model is suitable for developers building TCM‑focused applications and for academic studies requiring domain‑specific inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.1 GB 30.4 GB
Too big Get file →
Q3_K_S34.5 GB 35.9 GB
Too big Get file →
Q3_K_M38.2 GB 39.5 GB
Too big Get file →
Q3_K_L41.2 GB 42.5 GB
Too big Get file →
IQ4_XS43.1 GB 44.4 GB
Too big Get file →
Q4_K_S45.5 GB 46.8 GB
Too big Get file →
Q4_K_M48.4 GB 49.7 GB
Too big Get file →
Q5_K_S55.0 GB 56.3 GB
Too big Get file →
Q5_K_M56.7 GB 58.0 GB
Too big Get file →
Q6_K65.5 GB 66.8 GB
Too big Get file →
Q8_084.8 GB 86.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (45.48 GB file, ~46.8 GB memory). For 12 GB VRAM use Q4_K_M (48.41 GB file, ~49.7 GB memory). For 16 GB VRAM use Q5_K_M (56.71 GB file, ~58 GB memory). Estimates are approximate.

What GPU do you need for DeepPulse 80B Thinking V0.1?

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: the best quant that fits is Q2_K (29.1 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (45.5 GB file, about 46.8 GB in use).

Which DeepPulse 80B Thinking V0.1 quant should you choose?

Q4_K_M is the usual starting point for DeepPulse 80B Thinking V0.1: it balances file size and quality well. Here it is a 48.4 GB file.

The Q8_0 file is 84.8 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 29.1 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

Architectureqwen3next
Parameters79.7B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyDeeppulse
Licenseapache-2.0
Downloads (HF)619
Last updated2026-10-16

Frequently asked questions about DeepPulse 80B Thinking V0.1

How much VRAM does DeepPulse 80B Thinking V0.1 need?

About 49.7 GB at Q4_K_M with an 8K context window. That is the 48.4 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 DeepPulse 80B Thinking V0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepPulse 80B Thinking V0.1 GGUF?

It depends on the quant: Q2_K is 29.1 GB, Q3_K_S is 34.5 GB, Q3_K_M is 38.2 GB, Q3_K_L is 41.2 GB, IQ4_XS is 43.1 GB, Q4_K_S is 45.5 GB and 5 more.

What context length does DeepPulse 80B Thinking V0.1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download DeepPulse 80B Thinking V0.1 GGUF?

The files are on Hugging Face in the mradermacher/DeepPulse-80B-Thinking-V0.1-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 DeepPulse 80B Thinking V0.1 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 DeepPulse 80B on 8 GB VRAM?

Use the Q4_K_S quant, which requires about 46.8 GB of VRAM at 8k context. It will not fit on 8 GB VRAM.

Does the model support vision tasks?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Deeppulse models

All Deeppulse →

Other large models

All large models →