license: apache-2.0
tags:
- transformers
- gguf
- qwen3
- thinkingcap
- efficient-thinking
- reasoning
- token-efficient
- lora
- sft
- abliterated
- multi-token-prediction
- mtp
- llama.cpp
- text-generation
base_model: - hotdogs/Qwen3.8-27B-thinkingcap-abliterated-preview
model: - hotdogs/Qwen3.8-27B-thinkingcap-abliterated-preview-mtp-GGUF
datasets: - hotdogs/thinkingcap-sft-qwen38-27b
pretty_name: Qwen3.8-27B ThinkingCap Abliterated (MTP GGUF)
Qwen3.8-27B ThinkingCap Abliterated (MTP GGUF)
llama.cpp GGUF from the ThinkingCap SFT-merged model
(hotdogs/Qwen3.8-27B-thinkingcap-abliterated-preview).
Trained from the on-policy oracle-verified dataset.
All 3 quantizations preserve the MTP layer (blk.64, 15 tensors
including 4 nextn.* projection tensors). 866 tensors total, 27.3B params.
Files
| File | Size | BPW | Notes |
|---|---|---|---|
| Qwen3.8-27B-thinkingcap-abliterated-preview-mtp-f16.gguf | 51 GB | 16.0 | lossless |
| Qwen3.8-27B-thinkingcap-abliterated-preview-mtp-Q6_K.gguf | 21 GB | 6.56 | best quality/size |
| Qwen3.8-27B-thinkingcap-abliterated-preview-mtp-Q4_K_M.gguf | 16 GB | ~5.1 | fastest |
MTP verification
import gguf
g = gguf.GGUFReader("Qwen3.8-27B-thinkingcap-abliterated-preview-mtp-f16.gguf")
mtp = [t.name for t in g.tensors if 'blk.64' in t.name]
print(len(mtp)) # 15
Serve (llama.cpp)
CUDA_VISIBLE_DEVICES=0,1,2,3,4 llama-server \
-m Qwen3.8-27B-thinkingcap-abliterated-preview-mtp-Q6_K.gguf \
--n-gpu-layers 999 --ctx-size 8192 --parallel 2 \
--batch-size 4096 --flash-attn on \
--temp 1 --top-k 20 --top-p 0.95 --min-p 0.0 --jinja
Smoke test
| Problem | Think chars | Answer | Correct |
|---|---|---|---|
| 27 x 43 | 163 | 1161 | Yes |
| bat + ball = 1.10, bat = ball + 1.00 | 161 | ball = 0.05 | Yes |
| snail 10m wall, +3m day, -2m night | 359 | day 5 | Yes |
Base model (pre-SFT) used 4000+ think-chars on the snail problem.
ThinkingCap SFT brings it to 359 (-91%).