empero-ai
Qwen3.8 4B Distill
Qwen3.8 4B Distill is a 4.33B dense qwen35 model from empero-ai. Configured context length is 262,144 tokens. License: apache-2.0. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters4.3B
Context256K
Attentionhybrid
Licenseapache-2.0
32 layers · 4 KV heads · head dim 256 · 24 linear-attention layers · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 8.07 GB | Hugging Face file bytes |
| Q8_0 | 4.29 GB | Hugging Face file bytes |
| Q6_K | 3.32 GB | Hugging Face file bytes |
| Q5_K_M | 2.94 GB | Hugging Face file bytes |
| Q4_K_M | 2.59 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Runs | Q8_0 | 32–44 |
| GeForce RTX 3060 12GB | Runs | BF16 | 22–30 |
| GeForce RTX 4060 Ti 16GB | Runs great | BF16 | 18–24 |
| GeForce RTX 4090 | Runs great | BF16 | 62–85 |
| GeForce RTX 5090 | Runs great | BF16 | 110–150 |
| Apple M4 Pro | Runs great | BF16 | 17–23 |
| Apple M5 | Runs | BF16 | 9.4–13 |
| CPU only · DDR5-5600 | Runs on CPU | BF16 | 5.5–7.5 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Tight fit, Q8_0, 19–26 tok/s
- GeForce RTX 2060 6GB — Tight fit, Q8_0, 38–52 tok/s
- GeForce GTX 1660 Super — Tight fit, Q8_0, 38–52 tok/s
- GeForce GTX 1660 Ti — Tight fit, Q8_0, 32–44 tok/s
- Intel Arc A380 — Tight fit, Q8_0, 21–29 tok/s
- GeForce RTX 5060 Ti 8GB — Runs, Q8_0, 51–69 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (BF16).
llama.cpp
llama-server -hf empero-ai/Qwen3.8-4B-Distill-GGUF:BF16 -c 8192 -ngl 32
Ollama
ollama run qwen3.8
LM Studio
lms get empero-ai/Qwen3.8-4B-Distill-GGUF # Then load quant BF16