Qwen
Qwen3.5 122B A10B
Qwen3.5 122B A10B is an open-weights 122B-parameter model by Qwen. It is listed as in-progress on the local.ai leaderboard.
MoEopen weights
Parameters
122B
MoE · 10B active parameters
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-04-24
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 70.8GQ6_K 109.8GQ8_0 134.2GFP16 244G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 32.9 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 43.9 GB | Very small |
| Q3_K_M | 56.1 GB | Small |
| NVFP4 | 61 GB | NVIDIA 4-bit |
| Q4_K_S | 65.9 GB | Common |
| Q4_K_M | 70.8 GB | Most common sweet spot |
| Q5_K_M | 92.7 GB | Balanced |
| Q6_K | 109.8 GB | Near-lossless |
| Q8_0 | 134.2 GB | Near-lossless |
| FP16 | 244 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model.safetensors-00025-of-00039.safetensors | 6.00 GB |
| model.safetensors-00026-of-00039.safetensors | 6.00 GB |
| model.safetensors-00027-of-00039.safetensors | 6.00 GB |
| model.safetensors-00028-of-00039.safetensors | 6.00 GB |
| model.safetensors-00029-of-00039.safetensors | 6.00 GB |
| model.safetensors-00030-of-00039.safetensors | 6.00 GB |
GGUF: unsloth/Qwen3.5-122B-A10B-GGUF · 307,349 downloads
| File | Size | |
|---|---|---|
| BF16/Qwen3.5-122B-A10B-BF16-00001-of-00005.gguf | 46.51 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00002-of-00005.gguf | 46.50 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00003-of-00005.gguf | 46.50 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00004-of-00005.gguf | 46.50 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00005-of-00005.gguf | 41.52 GB | download |
| MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00001-of-00003.gguf | 0.01 GB | download |
| MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00002-of-00003.gguf | 46.23 GB | download |
| MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00003-of-00003.gguf | 23.30 GB | download |
| Q3_K_M/Qwen3.5-122B-A10B-Q3_K_M-00001-of-00003.gguf | 0.01 GB | download |
| Q3_K_M/Qwen3.5-122B-A10B-Q3_K_M-00002-of-00003.gguf | 46.18 GB | download |
| Q3_K_M/Qwen3.5-122B-A10B-Q3_K_M-00003-of-00003.gguf | 6.35 GB | download |
| Q3_K_S/Qwen3.5-122B-A10B-Q3_K_S-00001-of-00003.gguf | 0.01 GB | download |
GGUF: unsloth/Qwen3.5-122B-A10B-MTP-GGUF · 167,867 downloads
| File | Size | |
|---|---|---|
| BF16/Qwen3.5-122B-A10B-BF16-00001-of-00005.gguf | 46.51 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00002-of-00005.gguf | 46.50 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00003-of-00005.gguf | 46.50 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00004-of-00005.gguf | 46.50 GB | download |
| BF16/Qwen3.5-122B-A10B-BF16-00005-of-00005.gguf | 46.23 GB | download |
| MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00001-of-00003.gguf | 0.01 GB | download |
| MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00002-of-00003.gguf | 46.26 GB | download |
| MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00003-of-00003.gguf | 24.73 GB | download |
| Q8_0/Qwen3.5-122B-A10B-Q8_0-00001-of-00004.gguf | 0.01 GB | download |
| Q8_0/Qwen3.5-122B-A10B-Q8_0-00002-of-00004.gguf | 46.36 GB | download |
| Q8_0/Qwen3.5-122B-A10B-Q8_0-00003-of-00004.gguf | 46.39 GB | download |
| Q8_0/Qwen3.5-122B-A10B-Q8_0-00004-of-00004.gguf | 30.69 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.