Hermes 4.3 36B needs about 24.4 GB of memory at Q4_K_M (a 21.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 28 quants, from 0.0 GB to 72.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Hermes 4.3 36B – a large reasoning‑focused model
Hermes 4.3 36B is a 36 billion‑parameter model based on ByteDance Seed 36B. It is trained for hybrid reasoning, math, code, STEM, logic, and structured JSON output. The model is open, steerable, and licensed under Apache‑2.0.
Good at
- Hybrid reasoning with explicit deliberation segments
- High‑quality math, code, and STEM responses
- Structured JSON output and schema repair
Limits
- Requires large VRAM for higher‑quality quants
- No vision or audio capabilities
- Training context limited to 524,288 tokens
Best for
- Complex problem solving in technical domains
- Generating structured data in JSON format
- Steerable assistant tasks with low refusal rates
Who it’s for. Developers and researchers needing a large, open‑source reasoning model for technical and structured output tasks. The model is suitable for applications that can accommodate its VRAM requirements and benefit from its hybrid reasoning mode.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ2_XXS | 9.9 GB | 12.6 GB | Too big | Get file → | |
| IQ2_XS | 10.9 GB | 13.6 GB | Too big | Get file → | |
| IQ2_S | 11.6 GB | 14.3 GB | Too big | Get file → | |
| IQ2_M | 12.5 GB | 15.2 GB | Too big | Get file → | |
| Q2_K | 13.6 GB | 16.3 GB | Too big | Get file → | |
| IQ3_XXS | 14.1 GB | 16.8 GB | Too big | Get file → | |
| Q2_K_L | 14.4 GB | 17.0 GB | Too big | Get file → | |
| IQ3_XS | 15.1 GB | 17.7 GB | Too big | Get file → | |
| Q3_K_S | 15.9 GB | 18.5 GB | Too big | Get file → | |
| IQ3_M | 16.5 GB | 19.1 GB | Too big | Get file → | |
| Q3_K_M | 17.6 GB | 20.3 GB | Too big | Get file → | |
| Q3_K_L | 19.1 GB | 21.8 GB | Too big | Get file → | |
| IQ4_XS | 19.5 GB | 22.1 GB | Too big | Get file → | |
| Q3_K_XL | 19.8 GB | 22.5 GB | Too big | Get file → | |
| IQ4_NL | 20.6 GB | 23.2 GB | Too big | Get file → | |
| Q4_0 | 20.6 GB | 23.3 GB | Too big | Get file → | |
| Q4_K_S | 20.7 GB | 23.3 GB | Too big | Get file → | |
| Q4_K_M | 21.8 GB | 24.4 GB | Too big | Get file → | |
| Q4_K_L | 22.4 GB | 25.0 GB | Too big | Get file → | |
| Q4_1 | 22.8 GB | 25.4 GB | Too big | Get file → | |
| Q5_K_S | 25.0 GB | 27.6 GB | Too big | Get file → | |
| Q5_K_M | 25.6 GB | 28.2 GB | Too big | Get file → | |
| Q5_K_L | 26.1 GB | 28.7 GB | Too big | Get file → | |
| Q6_K | 29.7 GB | 32.3 GB | Too big | Get file → | |
| Q6_K_L | 30.1 GB | 32.7 GB | Too big | Get file → | |
| Q8_0 | 38.4 GB | 41.1 GB | Too big | Get file → | |
| BF16 | 72.3 GB (2 parts) | 75.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (9.91 GB file, ~12.6 GB memory). For 12 GB VRAM, IQ2_XS or IQ2_S are suitable. For 16 GB VRAM, Q2_K or IQ3_XXS provide a balance of size and performance. Higher‑quality quants such as Q4_K_M or Q5_K_M require 24–28 GB VRAM.
What GPU do you need for Hermes 4.3 36B?
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 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_M (12.5 GB file, about 15.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_S (20.7 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_L (26.1 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (38.4 GB file, about 41.1 GB in use).
Which Hermes 4.3 36B quant should you choose?
Q4_K_M is the usual starting point for Hermes 4.3 36B: it balances file size and quality well. Here it is a 21.8 GB file.
The Q8_0 file is 38.4 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 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
Source
Frequently asked questions about Hermes 4.3 36B
How much VRAM does Hermes 4.3 36B need?
About 24.4 GB at Q4_K_M with an 8K context window. That is the 21.8 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 4.3 36B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hermes 4.3 36B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 9.9 GB, IQ2_XS is 10.9 GB, IQ2_S is 11.6 GB, IQ2_M is 12.5 GB, Q2_K is 13.6 GB and 22 more.
What context length does Hermes 4.3 36B support?
The GGUF header lists a trained context length of 524,288 tokens (512K). 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 Hermes 4.3 36B GGUF?
The files are on Hugging Face in the bartowski/NousResearch_Hermes-4.3-36B-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 4.3 36B 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 4.3 36B on 8 GB VRAM?
Use the IQ2_XXS quant, which is 9.91 GB and requires about 12.6 GB of VRAM at 8k context.
Does Hermes 4.3 36B support image input?
No, the model has no vision or audio capabilities.
What license applies to Hermes 4.3 36B?
The model is released under the Apache‑2.0 license.