unsloth
Qwen3 VL 235B A22B Instruct
Qwen3 VL 235B A22B Instruct is a 235.1B mixture-of-experts qwen3vlmoe model from unsloth, with about 22.0B parameters active per token. 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.
Parameters235B / 22.0B active
Context256K
Attentiongqa
Licenseapache-2.0
94 layers · 4 KV heads · head dim 128 · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 438.0 GB | Hugging Face file bytes |
| UD-Q8_K_XL | 251.2 GB | Hugging Face file bytes |
| Q8_0 | 232.8 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 186.7 GB | Hugging Face file bytes |
| Q6_K | 179.8 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 155.4 GB | Hugging Face file bytes |
| Q5_K_M | 155.4 GB | Hugging Face file bytes |
| Q5_K_S | 150.8 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 124.9 GB | Hugging Face file bytes |
| Q4_K_M | 132.4 GB | Hugging Face file bytes |
| Q4_K_S | 124.5 GB | Hugging Face file bytes |
| IQ4_NL | 123.5 GB | Hugging Face file bytes |
| IQ4_XS | 116.7 GB | Hugging Face file bytes |
| Q4_1 | 137.1 GB | Hugging Face file bytes |
| Q4_0 | 124.0 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 96.6 GB | Hugging Face file bytes |
| Q3_K_M | 104.7 GB | Hugging Face file bytes |
| Q3_K_S | 94.5 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 88.1 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 82.0 GB | Hugging Face file bytes |
| Q2_K | 159.7 GB | Hugging Face file bytes |
| UD-IQ1_M | 64.8 GB | Hugging Face file bytes |
| UD-IQ1_S | 58.5 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 3060 12GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 4060 Ti 16GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 4090 | Won't fit | UD-IQ1_S | — |
| GeForce RTX 5090 | Won't fit | UD-IQ1_S | — |
| Apple M4 Pro | Won't fit | UD-IQ1_S | — |
| Apple M5 | Won't fit | UD-IQ1_S | — |
| CPU only · DDR5-5600 | Won't fit | UD-IQ1_S | — |
Smallest devices that fit it fully
- NVIDIA H100 SXM 80GB — Tight fit, UD-IQ1_M, 228–311 tok/s
- NVIDIA H100 PCIe 80GB — Tight fit, UD-IQ1_M, 136–185 tok/s
- NVIDIA A100 80GB SXM — Tight fit, UD-IQ1_M, 139–189 tok/s
- NVIDIA A100 80GB PCIe — Tight fit, UD-IQ1_M, 132–179 tok/s
- Apple M3 Ultra — Tight fit, UD-IQ1_M, 56–76 tok/s
- NVIDIA H200 SXM — Tight fit, UD-Q4_K_XL, 187–255 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (UD-IQ1_S).
llama.cpp
llama-server -hf unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF:UD-IQ1_S -c 2048 -ngl 0
Ollama
ollama run qwen3
LM Studio
lms get unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF # Then load quant UD-IQ1_S