Qwen
Qwen3.6 35B A3B
Qwen3.6 35B A3B is an open-weights 35B-parameter model by Qwen. It holds an Intelligence score of 74.9 on the local.ai leaderboard (2026-08 snapshot).
MoEopen weights
74.9
local.ai Intelligence
Parameters
35B
MoE · 3B 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 20.3GQ6_K 31.5GQ8_0 38.5GFP16 70G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 9.5 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 12.6 GB | Very small |
| Q3_K_M | 16.1 GB | Small |
| NVFP4 | 17.5 GB | NVIDIA 4-bit |
| Q4_K_S | 18.9 GB | Common |
| Q4_K_M | 20.3 GB | Most common sweet spot |
| Q5_K_M | 26.6 GB | Balanced |
| Q6_K | 31.5 GB | Near-lossless |
| Q8_0 | 38.5 GB | Near-lossless |
| FP16 | 70 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model-00001-of-00026.safetensors | 3.72 GB |
| model-00006-of-00026.safetensors | 3.69 GB |
| model-00016-of-00026.safetensors | 3.68 GB |
| model-00008-of-00026.safetensors | 3.68 GB |
| model-00010-of-00026.safetensors | 3.68 GB |
| model-00018-of-00026.safetensors | 3.68 GB |
GGUF: unsloth/Qwen3.6-35B-A3B-GGUF · 1,135,209 downloads
| File | Size | |
|---|---|---|
| BF16/Qwen3.6-35B-A3B-BF16-00001-of-00002.gguf | 46.49 GB | download |
| BF16/Qwen3.6-35B-A3B-BF16-00002-of-00002.gguf | 18.13 GB | download |
| Qwen3.6-35B-A3B-MXFP4_MOE.gguf | 20.22 GB | download |
| Qwen3.6-35B-A3B-Q8_0.gguf | 34.37 GB | download |
| Qwen3.6-35B-A3B-UD-IQ1_M.gguf | 9.36 GB | download |
| Qwen3.6-35B-A3B-UD-IQ2_M.gguf | 10.73 GB | download |
| Qwen3.6-35B-A3B-UD-IQ2_XXS.gguf | 10.02 GB | download |
| Qwen3.6-35B-A3B-UD-IQ3_S.gguf | 12.74 GB | download |
| Qwen3.6-35B-A3B-UD-IQ3_XXS.gguf | 12.30 GB | download |
| Qwen3.6-35B-A3B-UD-IQ4_NL.gguf | 16.80 GB | download |
| Qwen3.6-35B-A3B-UD-IQ4_NL_XL.gguf | 18.16 GB | download |
| Qwen3.6-35B-A3B-UD-IQ4_XS.gguf | 16.51 GB | download |
GGUF: LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF · 740,390 downloads
| File | Size | |
|---|---|---|
| Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact.gguf | 16.23 GB | download |
| Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX.gguf | 23.95 GB | download |
| Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact.gguf | 17.06 GB | download |
| Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX.gguf | 24.79 GB | download |
| Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P.gguf | 40.61 GB | download |
| mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf | 0.84 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.