GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
DavidAU
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
DavidAU
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
[ in final testing ... GGUFS/GGUF repo opening soon. ]
IMPORTANT: The GAIN method of training (AKA COLD FUSION) maintains 99% of performance of BF16, at both 8 bit and 4 bit levels. THIS MODEL exceeds performance of both 9B and 27B Qwen 3.5 AND Qwen 3.6 27B/35B-A3B models.
Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0 [working title]
This model uses the "GAIN" method of training, invented during the build of Qwen 3.6 27B Fable Fusion 711 (1900+ likes, 2.5 million + downloads, 60+ quant repos).
The "GAIN" method (programming) automatically (and dynamically) changes training on a per sample basis in real time during training AS THE MODEL LEARNS. This was designed to be used with all model types and datasets and plugs into the Unsloth training "stream".
The method improved metrics as well as overall model performance without overcooking or damaging the model.
This has also resulted, in the strongest and most stable model at both 4 bit and 8 bit and made 4 bit performance 99% of 8 bit performance too.
And it is a HERETIC too: Refusals: 8/100, KL divergence: 0.0048
THREE example generations at the bottom of the page.
NOTE:
This model version's benchs (for 8 bit) will be slightly lower than Qwen 3.6-27B-Fable-Fusion because of post Heretic'ing and additional training (noted below). Interestingly, some of the 4 bit benchs are HIGHER.
markdown
arc/c arc/e boolq hswag obkqa piqa winoQwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0 [instruct mode]mxfp8 0.702,0.876,0.911,0.793,0.502,0.818,0.760mxfp4 0.702,0.871,0.911,0.785,0.502,0.817,0.758NON-GAIN METHOD OF TRAINING, same datasets/same training settings.Qwen3.6-27B-V1.01-FF711-Dark-Hero-H2.0 (x.xxx = pending)mxfp8 0.701,x.xxx,x.xxx,0.789,0.504,0.819,0.750mxfp4 0.692,0.858,0.910,0.782,0.492,0.809,0.753Qwen3.6-27B-Instruct: [base, non heretic][instruct mode]mxfp8 0.647,0.803,0.910,0.773,0.450,0.806,0.742Qwen3.6-35B-A3B-Instruct [base, non heretic][instruct mode]mxfp8 0.581,0.757,0.892,0.751,0.428,0.803,0.688Qwen3.5-27B-Instruct: [base, non heretic][instruct mode]mxfp8 0.557,0.711,0.868,0.533,0.452,0.706,0.695
NOTES:
This GAIN method of training was first tested on an Qwen 3.5 9B model:
which showed outstanding performance even exceeding the Qwen 3.5 9B Defiant Fable - which is, in itself record breaking (360+ likes, 400k+ downloads) which operates above Qwen 3.5 27B performance levels already.
This version (also the first test of GAIN on 27B model) is built on the Qwen 3.6 27B Fable Fusion 711 core directly, it has:
Q4ks, non imatrix, default Qwen settings
This is "4 bit" performance at the lower end of the scale, expect better with Imatrix and/or higher quants.
WARNING:
NSFW, R-18 Swearing - TOTALLY Unfiltered !!
Example #1 of 3
THINKING BLOCK:
Thought for 1.41 seconds
The user wants me to write a persuasive, high-energy pitch for why they should use me to write their fictional story. They want:
Let me craft this with maximum confidence, swagger, and edge. I'll make it visually striking with formatting, use profanity liberally, and really sell myself as the ultimate AI writing partner.
OUTPUT:
Example 2 of 3
Thought for 7.52 seconds
Example 3 of 3
Thought for 2.78 seconds