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)
τ²-bench
99%
GAIA
74%
GDPval
71%
HuggingFace metadata · updated 2026-04-24
repo
Qwen/Qwen3.6-35B-A3B
license
apache-2.0
downloads
5,873,711
likes
2,688

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 sizeNote
IQ2_XXS9.5 GBExtreme compression, largest quality loss
IQ3_XXS12.6 GBVery small
Q3_K_M16.1 GBSmall
NVFP417.5 GBNVIDIA 4-bit
Q4_K_S18.9 GBCommon
Q4_K_M20.3 GBMost common sweet spot
Q5_K_M26.6 GBBalanced
Q6_K31.5 GBNear-lossless
Q8_038.5 GBNear-lossless
FP1670 GBOriginal weights

Actual files on HuggingFace

FileSize
model-00001-of-00026.safetensors3.72 GB
model-00006-of-00026.safetensors3.69 GB
model-00016-of-00026.safetensors3.68 GB
model-00008-of-00026.safetensors3.68 GB
model-00010-of-00026.safetensors3.68 GB
model-00018-of-00026.safetensors3.68 GB
GGUF: unsloth/Qwen3.6-35B-A3B-GGUF · 1,135,209 downloads
FileSize
BF16/Qwen3.6-35B-A3B-BF16-00001-of-00002.gguf46.49 GBdownload
BF16/Qwen3.6-35B-A3B-BF16-00002-of-00002.gguf18.13 GBdownload
Qwen3.6-35B-A3B-MXFP4_MOE.gguf20.22 GBdownload
Qwen3.6-35B-A3B-Q8_0.gguf34.37 GBdownload
Qwen3.6-35B-A3B-UD-IQ1_M.gguf9.36 GBdownload
Qwen3.6-35B-A3B-UD-IQ2_M.gguf10.73 GBdownload
Qwen3.6-35B-A3B-UD-IQ2_XXS.gguf10.02 GBdownload
Qwen3.6-35B-A3B-UD-IQ3_S.gguf12.74 GBdownload
Qwen3.6-35B-A3B-UD-IQ3_XXS.gguf12.30 GBdownload
Qwen3.6-35B-A3B-UD-IQ4_NL.gguf16.80 GBdownload
Qwen3.6-35B-A3B-UD-IQ4_NL_XL.gguf18.16 GBdownload
Qwen3.6-35B-A3B-UD-IQ4_XS.gguf16.51 GBdownload
GGUF: LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF · 740,390 downloads
FileSize
Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact.gguf16.23 GBdownload
Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX.gguf23.95 GBdownload
Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact.gguf17.06 GBdownload
Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX.gguf24.79 GBdownload
Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P.gguf40.61 GBdownload
mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf0.84 GBdownload

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.