QW

Hermes-4-14B

QwenGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters14.8B
Context40K
Layers40
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Hermes-4-14B needs about 11.3 GB of memory at Q4_K_M (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 0.0 GB to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Hermes‑4‑14B: a hybrid‑mode reasoning model based on Qwen3‑14B

Hermes‑4‑14B is a 14.8B‑parameter model derived from Qwen3‑14B. It supports reasoning, role‑play, and tool use. The model is trained with a large post‑training corpus focused on verified reasoning traces.

Good at

  • Reasoning and math
  • Code generation
  • Structured JSON output

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • Apache‑2.0 license

Best for

  • Complex problem solving
  • Agent‑style tool integration
  • Creative writing with structure

Who it’s for. Developers and researchers who need a large language model that excels in reasoning and structured output. The model is suitable for building agents that interact with external tools and for applications requiring high‑quality math and code responses.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ1_S4.3 GB 6.1 GB
Fits Get file →
IQ1_M4.8 GB 6.6 GB
Fits Get file →
IQ2_XXS4.9 GB 6.8 GB
Fits Get file →
IQ2_XS5.3 GB 7.1 GB
Fits Get file →
IQ2_S5.5 GB 7.3 GB
Tight Get file →
Q2_K_S5.7 GB 7.5 GB
Tight Get file →
IQ2_M5.7 GB 7.6 GB
Tight Get file →
Q2_K_M5.9 GB 7.7 GB
Tight Get file →
IQ3_XS6.7 GB 8.6 GB
Too big Get file →
Q3_K_S7.4 GB 9.2 GB
Too big Get file →
Q3_K_M7.6 GB 9.4 GB
Too big Get file →
Q4_K_S8.8 GB 10.7 GB
Too big Get file →
Q4_09.1 GB 10.9 GB
Too big Get file →
Q4_19.3 GB 11.2 GB
Too big Get file →
Q4_K_M9.5 GB 11.3 GB
Too big Get file →
Q5_010.7 GB 12.6 GB
Too big Get file →
Q5_K_M11.0 GB 12.9 GB
Too big Get file →
Q5_111.6 GB 13.4 GB
Too big Get file →
Q6_K_M12.5 GB 14.3 GB
Too big Get file →
Q8_015.7 GB 17.5 GB
Too big Get file →
BF1621.7 GB 23.5 GB
Too big Get file →
F1621.7 GB 23.5 GB
Too big Get file →
BF1629.5 GB 31.4 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_S (file size 8.85 GB, estimated 10.7 GB memory). For 16‑GB VRAM, Q5_K_M (file size 11.02 GB, estimated 12.9 GB memory) is a good balance. For 32‑GB VRAM, Q6_K_M (file size 12.5 GB, estimated 14.3 GB memory) provides higher precision.

What GPU do you need for Hermes-4-14B?

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: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K_M (5.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (9.5 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_M (12.5 GB file, about 14.3 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (21.7 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.4 GB in use).

Which Hermes-4-14B quant should you choose?

Q4_K_M is the usual starting point for Hermes-4-14B: it balances file size and quality well. Here it is a 9.5 GB file.

The Q8_0 file is 15.7 GB, about 1.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters14.8B
Layers40
Trained context40,960 tokens
KV cache (fp16)160 KB per token

Source

Quantized byMungert
FamilyQwen
Base modelQwen/Qwen3-14B
Licenseapache-2.0
Downloads (HF)1,803
Last updated2025-09-24

Frequently asked questions about Hermes-4-14B

How much VRAM does Hermes-4-14B need?

About 11.3 GB at Q4_K_M with an 8K context window. That is the 9.5 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 Hermes-4-14B on an 8 GB GPU?

Yes, with Q2_K_M: the 5.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hermes-4-14B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 4.3 GB, IQ1_M is 4.8 GB, IQ2_XXS is 4.9 GB, IQ2_XS is 5.3 GB, IQ2_S is 5.5 GB and 18 more.

What context length does Hermes-4-14B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Hermes-4-14B GGUF?

The files are on Hugging Face in the Mungert/Hermes-4-14B-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 Hermes-4-14B 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 Hermes‑4‑14B on 8 GB VRAM?

Use the Q4_K_S quantized file; it requires about 10.7 GB of VRAM at 8‑k context.

Does Hermes‑4‑14B support vision tasks?

No, the model has no vision capabilities.

What license applies to Hermes‑4‑14B?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3-14B

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other medium models

All medium models →