Instructions to use walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF

SGLang

How to use walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/walissoncasonatto/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP-GGUF
```

walissoncasonatto commited on 7 days ago

Commit

309b1d7

verified ·

1 Parent(s): 91d7257

README: remove internal references

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -73,7 +73,7 @@ Quantized from `huihui-ai/Huihui-Qwen3.6-27B-abliterated-MTP-GGUF` (Q8_0 variant
   --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0.0
 ```
-### Linux / DGX Spark / kneutral
 Same flags, drop the `.exe` and `^` line continuations. On GB10 (DGX Spark) also pass `--no-mmap` due to unified-memory mmap slowdowns.
@@ -83,7 +83,7 @@ Benchmarked on personal RTX 5090 (32 GB GDDR7, 1792 GB/s, sm_120a), Windows 11,
 ### Quality — multi-seed 90/90 PERFECT
-10 independent runs × 9 probes (q1q5 + reasoning) = **90/90 probes pass, 100%**, zero retries needed. Matches the multi-seed reference established on kneutral RTX PRO 6000 with the same base model. avgTPS during multi-seed: **93 t/s on q1q5, 95.9 t/s on reasoning suite**.
 ### Single-pass q1q5 smoke (representative timings)
@@ -114,7 +114,7 @@ MTP acceptance is **highly consistent (68-71% across all workload categories)**
 |---|---|---|---|---|
 | `s-batman/Qwen3.6-27B-NVFP4-MTP-GGUF` (Qwen base, not Huihui) | 14.64 GB | 105 t/s peak (different bench) | 90/90 multi-seed (2 retries) | Baseline Qwen quality |
 | `huihui-ai/Huihui-...-Q5_K.gguf` (this model, Q5_K_M) | 18.19 GB | 75-85 t/s | 5/5 q1q5 | Highly workload-dependent |
-| **`Huihui-...-NVFP4-MTP.gguf` (this repo)** | **19.65 GB** | **91-107 t/s** | **5/5 q1q5** | **Best balance: kneutral-validated quality + Blackwell-native speed + predictable acceptance** |
 ### VRAM

   --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0.0
 ```
+### Linux / DGX Spark
 Same flags, drop the `.exe` and `^` line continuations. On GB10 (DGX Spark) also pass `--no-mmap` due to unified-memory mmap slowdowns.
 ### Quality — multi-seed 90/90 PERFECT
+10 independent runs × 9 probes (q1q5 + reasoning) = **90/90 probes pass, 100%**, zero retries needed. avgTPS during multi-seed: **93 t/s on q1q5, 95.9 t/s on reasoning suite**.
 ### Single-pass q1q5 smoke (representative timings)
 |---|---|---|---|---|
 | `s-batman/Qwen3.6-27B-NVFP4-MTP-GGUF` (Qwen base, not Huihui) | 14.64 GB | 105 t/s peak (different bench) | 90/90 multi-seed (2 retries) | Baseline Qwen quality |
 | `huihui-ai/Huihui-...-Q5_K.gguf` (this model, Q5_K_M) | 18.19 GB | 75-85 t/s | 5/5 q1q5 | Highly workload-dependent |
+| **`Huihui-...-NVFP4-MTP.gguf` (this repo)** | **19.65 GB** | **91-107 t/s** | **5/5 q1q5** | **Best balance: abliterated quality + Blackwell-native speed + predictable acceptance** |
 ### VRAM