Qwen3.6-35B-A3B-NVFP4-MTP-GGUF
This repo contains two experimental NVFP4 GGUF quantizations of Qwen3.6-35B-A3B for llama.cpp. This was quantized using my experimental advanced-gguf-quantizer tool. Both models were imatrix calibrated for the first time using a new custom dataset that I am evaluating.
Params
—
Context
—
Downloads 30d
360 K
Likes
12
Download history
daily snapshots · 34 days
▲ 148 K in the last 30 days (69.5%)
397 K255 K
Aug 23Sep 2Sep 12Sep 21
397 K182 K
Aug 19Aug 30Sep 10Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Qwen3.6-35B-A3B-NVFP4-MTP-HQ.gguf | GGUF | 20.5 GB | 23.0 GB | ⚠️ Tight — reduce context |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run qwen3-6-35b-a3b-nvfp4-mtp-gguf # pin the quantization explicitly $ ollama run qwen3-6-35b-a3b-nvfp4-mtp-gguf-gguf
$ huggingface-cli download michaelw9999/Qwen3.6-35B-A3B-NVFP4-MTP-GGUF-GGUF \
Qwen3.6-35B-A3B-NVFP4-MTP-HQ.gguf --local-dir .
$ llama-cli -m Qwen3.6-35B-A3B-NVFP4-MTP-HQ.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-6-35b-a3b-nvfp4-mtp-gguf
{
"hf_id": "michaelw9999/Qwen3.6-35B-A3B-NVFP4-MTP-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 360082,
"vram_estimates": [
{ "quant": "GGUF", "gb": 23.0 }
],
"updated_at": "2026-08-19T01:00:38Z"
}
Specifications
- First seen on the Hub
- 2026-06-12
- Base model
- Qwen3.6-35B-A3B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-19
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model