unsloth
Qwen3.5 9B
Qwen3.5 9B is a 8.95B dense qwen35 model from unsloth. 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.
Parameters9.0B
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 | 16.7 GB | Hugging Face file bytes |
| UD-Q8_K_XL | 12.1 GB | Hugging Face file bytes |
| Q8_0 | 8.87 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 8.16 GB | Hugging Face file bytes |
| Q6_K | 6.95 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 6.28 GB | Hugging Face file bytes |
| Q5_K_M | 6.13 GB | Hugging Face file bytes |
| Q5_K_S | 5.92 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 5.56 GB | Hugging Face file bytes |
| Q4_K_M | 5.29 GB | Hugging Face file bytes |
| Q4_K_S | 5.02 GB | Hugging Face file bytes |
| IQ4_NL | 5.00 GB | Hugging Face file bytes |
| IQ4_XS | 4.81 GB | Hugging Face file bytes |
| Q4_1 | 5.44 GB | Hugging Face file bytes |
| Q4_0 | 5.01 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 4.71 GB | Hugging Face file bytes |
| Q3_K_M | 4.35 GB | Hugging Face file bytes |
| Q3_K_S | 4.02 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 3.74 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 3.84 GB | Hugging Face file bytes |
| UD-IQ2_XXS | 2.97 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Tight fit | UD-Q5_K_XL | 23–31 |
| GeForce RTX 3060 12GB | Tight fit | Q8_0 | 20–28 |
| GeForce RTX 4060 Ti 16GB | Tight fit | UD-Q8_K_XL | 12–16 |
| GeForce RTX 4090 | Runs | BF16 | 30–42 |
| GeForce RTX 5090 | Runs great | BF16 | 54–74 |
| Apple M4 Pro | Tight fit | BF16 | 8.3–11 |
| Apple M5 | Tight fit | Q8_0 | 8.6–12 |
| CPU only · DDR5-5600 | Runs on CPU | BF16 | 2.7–3.7 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Tight fit, Q3_K_M, 19–25 tok/s
- GeForce RTX 2060 6GB — Tight fit, Q3_K_M, 37–51 tok/s
- GeForce GTX 1660 Super — Tight fit, Q3_K_M, 37–51 tok/s
- GeForce GTX 1660 Ti — Tight fit, Q3_K_M, 32–44 tok/s
- Intel Arc A380 — Tight fit, Q3_K_M, 21–28 tok/s
- GeForce RTX 5060 Ti 8GB — Tight fit, UD-Q5_K_XL, 35–48 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (UD-Q8_K_XL).
llama.cpp
llama-server -hf unsloth/Qwen3.5-9B-GGUF:UD-Q8_K_XL -c 8192 -ngl 32
Ollama
ollama run qwen3.5
LM Studio
lms get unsloth/Qwen3.5-9B-GGUF # Then load quant UD-Q8_K_XL