unsloth / image-text-to-text updated 3 weeks ago

Qwen3.6-27B-NVFP4

Name: Qwen3.6-27B-NVFP4
Author: unsloth

2.5x faster throughput than other NVFP4 quants. This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. Works on a 24GB VRAM GPU. Benchmarks on 1xB200 128 concurrency.

Params

21.2 B

Context

—

Downloads 30d

3.4 M

Likes

267

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

3.4 M2.7 M

Jul 28Jul 31Aug 3Aug 6

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
model.safetensors	f8_e4m3	23.4 GB	29.4 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Qwen3_5ForConditionalGeneration
Parameters: 21.2 B
Tensor type: F8_E4M3
Licence: apache-2.0
First seen on the Hub: 2026-04-23
Base model: Qwen3.6-27B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen3.6-27B Qwen 7.0 M

Compare with

Qwen3.5-9B 12.4 M gemma-4-31B-it 11.9 M gemma-4-26B-A4B-it 11.7 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen3.6-27B-FP8 7.8 M Qwen3.6-27B 7.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB