Qwen3-235B-A22B — 235.1B Parameter Mixture of Experts LLM
Model Specifications
- Parameters
- 235.1B (22B active)
- Architecture
- Mixture of Experts
- Context Length
- 40K tokens
- Capabilities
- chat
- Release Date
- 2025-04-28
- Provider
- Alibaba
- Family
- qwen
VRAM Requirements
| Quantization | BPW | VRAM | Quality |
|---|---|---|---|
| IQ2_XXS | 2.38 | 70.4 GB | 65% |
| IQ2_M | 2.93 | 86.6 GB | 75% |
| Q2_K | 3.16 | 93.4 GB | 78% |
| IQ3_XXS | 3.25 | 96.0 GB | 82% |
| IQ3_XS | 3.5 | 103.3 GB | 84% |
| Q3_K_S | 3.64 | 107.5 GB | 85% |
| IQ3_M | 3.76 | 111.0 GB | 86% |
| Q3_K_M | 4 | 118.0 GB | 88% |
| Q3_K_L | 4.3 | 126.9 GB | 90% |
| IQ4_XS | 4.46 | 131.6 GB | 92% |
| Q4_K_S | 4.67 | 137.7 GB | 93% |
| Q4_K_M | 4.89 | 144.2 GB | 94% |
| Q5_K_S | 5.57 | 164.2 GB | 96% |
| Q5_K_M | 5.7 | 168.0 GB | 96% |
| Q6_K | 6.56 | 193.3 GB | 97% |
| Q8_0 | 8.5 | 250.3 GB | 100% |
| FP16 | 16 | 470.7 GB | 100% |
Benchmark Scores
HumanEval95.0
MMLU-PRO72.0
MATH96.0
IFEval88.0
GPQA66.0
Arena Elo1367.0
GPQA Diamond75.3
LiveCodeBench52.4
AIME71.7
MATH-50098.0
HLE10.6
AA Intelligence25.0
AA Coding22.1
AA Math71.7
How to Run Qwen3-235B-A22B
Run Qwen3-235B-A22B locally with Ollama (needs 144.2 GB VRAM at Q4_K_M):
ollama run qwen3:235.1bCompatible GPUs (13)
GPUs that can run Qwen3-235B-A22B at Q4_K_M quantization:
AMD Instinct MI300X(192GB, 5300 GB/s)Apple M2 Ultra (192GB)(192GB, 800 GB/s)Apple M3 Ultra (192GB)(192GB, 800 GB/s)Apple M4 Ultra (192GB)(192GB, 1092 GB/s)AMD Radeon Instinct MI300A(192GB, 10300 GB/s)AMD Radeon Instinct MI300X(192GB, 10300 GB/s)AMD Radeon Instinct MI308X(192GB, 10300 GB/s)Apple M5 Ultra (192GB)(192GB, 1228 GB/s)AMD Radeon Instinct MI325X(288GB, 10300 GB/s)AMD Radeon Instinct MI350X(288GB, 8190 GB/s)AMD Radeon Instinct MI355X(288GB, 8190 GB/s)Apple M4 Ultra (384GB)(384GB, 1092 GB/s)Apple M5 Ultra (384GB)(384GB, 1228 GB/s)