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

Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Name: Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF
Author: cdiamond

I built this quant because the ready-made FP4 file answered the wrong question. It was fast, but on my short WikiText-2 control it scored 6.4949 PPL. Plain Q40 scored 6.3798. The first higher-quality hybrid went too far the other way: good perplexity, 34.19 tok/s, and no comfortable room for 256K plus vision.

Params

—

Context

—

Downloads 30d

2.1 M

Likes

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

Download history

daily snapshots · 8 days

2.1 M1.0 M

Sep 2Sep 4Sep 7Sep 9

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
Qwen3.8-27B-iMatrix-NVFP4-MTP.gguf	GGUF	17.1 GB	19.3 GB	✅ Runs comfortably

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

Specifications

Licence: apache-2.0
First seen on the Hub: 2026-08-17
Base model: Qwen3.8-27B
Training datasets: undisclosed
Added to our catalog: 2026-09-02

Family

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

Base Qwen3.8-27B Qwen 6.7 M

Compare with

Qwen3-VL-8B-Instruct 15.2 M Qwen3.6-35B-A3B-FP8 12.4 M Qwen3.5-9B 11.4 M gemma-4-31B-it 8.7 M gemma-4-26B-A4B-it 8.6 M Qwen2.5-VL-7B-Instruct 7.7 M

Appears in

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