bartowski
NousResearch Hermes 4 14B
NousResearch Hermes 4 14B is a 14.8B dense qwen3 model from bartowski. Configured context length is 40,960 tokens. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters14.8B
Context40K
Attentiongqa
Licensesee the repo
40 layers · 8 KV heads · head dim 128 · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 27.5 GB | Hugging Face file bytes |
| Q8_0 | 14.6 GB | Hugging Face file bytes |
| Q6_K | 22.9 GB | Hugging Face file bytes |
| Q5_K_M | 9.79 GB | Hugging Face file bytes |
| Q5_K_S | 9.56 GB | Hugging Face file bytes |
| Q4_K_M | 8.38 GB | Hugging Face file bytes |
| Q4_K_S | 7.98 GB | Hugging Face file bytes |
| IQ4_NL | 7.95 GB | Hugging Face file bytes |
| IQ4_XS | 7.55 GB | Hugging Face file bytes |
| Q4_1 | 8.74 GB | Hugging Face file bytes |
| Q4_0 | 7.96 GB | Hugging Face file bytes |
| Q3_K_L | 7.36 GB | Hugging Face file bytes |
| Q3_K_M | 6.82 GB | Hugging Face file bytes |
| IQ3_M | 6.41 GB | Hugging Face file bytes |
| Q3_K_S | 6.20 GB | Hugging Face file bytes |
| IQ3_XXS | 5.53 GB | Hugging Face file bytes |
| Q2_K | 11.4 GB | Hugging Face file bytes |
| IQ2_S | 4.62 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Tight fit | IQ3_XXS | 24–33 |
| GeForce RTX 3060 12GB | Tight fit | Q5_K_S | 18–25 |
| GeForce RTX 4060 Ti 16GB | Runs | Q5_K_M | 13–18 |
| GeForce RTX 4090 | Runs | Q8_0 | 33–44 |
| GeForce RTX 5090 | Tight fit | BF16 | 33–44 |
| Apple M4 Pro | Tight fit | Q8_0 | 8.8–12 |
| Apple M5 | Tight fit | Q5_K_S | 7.7–10 |
| CPU only · DDR5-5600 | Runs on CPU | Q8_0 | 2.9–3.9 |
Smallest devices that fit it fully
- GeForce RTX 5060 Ti 8GB — Tight fit, IQ3_XXS, 37–51 tok/s
- GeForce RTX 5060 — Tight fit, IQ3_XXS, 37–51 tok/s
- GeForce RTX 5050 — Tight fit, IQ3_XXS, 27–36 tok/s
- GeForce RTX 4060 Ti 8GB — Tight fit, IQ3_XXS, 24–33 tok/s
- GeForce RTX 4060 — Tight fit, IQ3_XXS, 23–31 tok/s
- GeForce RTX 3070 Ti — Tight fit, IQ3_XXS, 51–69 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (Q5_K_M).
llama.cpp
llama-server -hf bartowski/NousResearch_Hermes-4-14B-GGUF:Q5_K_M -c 8192 -ngl 40
No matching name in the Ollama library snapshot.
LM Studio
lms get bartowski/NousResearch_Hermes-4-14B-GGUF # Then load quant Q5_K_M