GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nDimensional
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nDimensional
Model Tree
HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
| Architecture | Qwen3.5 dense hybrid attention (24 GDN + 8 full standard attention layers) |
| Parameters | 9B |
| Base model | Qwen/Qwen3.5-9B |
| Source GGUF | HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive |
| Format | BF16 |
| Conversion type | Lossless GGUF to safetensors conversion + merge with base model vision layers. |
Converted using code release coming soon, which reverses transforms applied during HF -> GGUF conversion.
The vision encoder weights are copied directly from the official Qwen/Qwen3.5-9B base model, after confirming the vision encoder (mmproj) was not modified in the source GGUF.
| Field | Base Model | This Model | Reason |
|---|---|---|---|
mtp_num_hidden_layers | 1 | 0 | Multi-Token Prediction (MTP) weights are stripped during GGUF export; disabled to prevent missing-tensor errors |
All other config fields are identical to the official Qwen3.5-9B.
Every converted tensor was compared against the official Qwen3.5-9B weights to verify transform conversiion correctness and characterize the moddifications made by the GGUF author. Since this is a BF16 -> BF16 conversion, after correcting transforms errors from GGUF noise; any non-zero difference represents an intentional modification to the weights.
| Tensor | Max Diff | Mean Diff | Status |
|---|---|---|---|
self_attn.o_proj.weight | 5.18e-02 | 6.51e-04 | ⚠️ Modified |
linear_attn.norm.weight | 1.95e-03 | 9.75e-04 | ⚠️ Modified |
Note: The spot-check only covers layers 0 and 3. A full per-layer analysis across all 32 layers was not needed for purpose of conversion verification. Other layers may contain similar weight modifications.
model.visual.* tensors are copied directly from the official Qwen3.5-9B model.embed_tokens.weight and lm_head.weight are bit-identical.gate_proj, up_proj, down_proj weights checked are bit-identical.