Qwen3.8-27B-FP8 vs Tiel-Coder-35B-A3B-GGUF-MTP

Specs, VRAM requirements and download trends — updated 10 November 2026.

Qwen · A · Open weights
Params
27.8 B
Context
—
30d
5.3 M
apache-2.0 · commercial OK
peculiar-ragdoll · B · Open weights
Params
35.0 B
Context
—
30d
3.1 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.8-27B-FP8 Tiel-Coder-35B-A3B-GGUF-MTP
Parameters 27.8 B 35.0 B
Architecture Qwen3_5ForConditionalGeneration —
Context length — —
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages — 2
Downloads 30d 5,285,294 3,054,347
Downloads all time 17.6 M 5.2 M
Quantizations on the Hub SAFETENSORS GGUF
Gated No No
First seen on the Hub 2026-08-13 2026-08-24

Download trend

Daily snapshots, last 83 days (20 Aug – 10 Nov)

7.9 M853 K
Qwen3.8-27B-FP8 Tiel-Coder-35B-A3B-GGUF-MTP

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Tiel-Coder-35B-A3B-GGUF-MTP · Q4_K_S 29.2 GB / 24 GB
❌ Won’t fit
Qwen3.8-27B-FP8 · fp16 38.6 GB / 24 GB
❌ Won’t fit

Adjacent comparisons