Qwen3.6-35B-A3B vs Dirk-Qwen3.8-27B-GGUF

Specs, VRAM requirements and download trends — updated 24 October 2026.

Qwen · A · Open weights
Params
36.0 B
Context
—
30d
3.7 M
apache-2.0 · commercial OK
peculiar-ragdoll · B · Open weights
Params
27.0 B
Context
—
30d
1.3 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B Dirk-Qwen3.8-27B-GGUF
Deployment Open weights · also via API Open weights
Parameters 36.0 B 27.0 B
Architecture Qwen3_5MoeForConditionalGeneration —
Context length 262,144 —
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages — 2
Downloads 30d 3,733,341 1,296,476
Downloads all time 32.3 M 2.2 M
Quantizations on the Hub SAFETENSORS GGUF
Gated No No
First seen on the Hub 2026-04-15 2026-08-14
API input price / 1M tokens $0.10 not on OpenRouter
API output price / 1M tokens $0.95 not on OpenRouter
Est. cost per 1M input + 1M output tokens $1.05 not on OpenRouter
Cached input / 1M tokens $0.05 not on OpenRouter
AA Intelligence Index 18.2 not on OpenRouter
AA Coding Index 41.9 not on OpenRouter
AA Agentic Index 13.1 not on OpenRouter
Max output tokens 235,929 not on OpenRouter
API providers 10 not on OpenRouter
Tool calling Yes not on OpenRouter
Reasoning mode Yes not on OpenRouter

API cost

Estimated cost of 1M input + 1M output tokens via OpenRouter

Qwen3.6-35B-A3B $1.05

Download trend

Daily snapshots, last 89 days (28 Jul – 24 Oct)

6.2 M862 K
Qwen3.6-35B-A3B Dirk-Qwen3.8-27B-GGUF

VRAM side by side

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

Dirk-Qwen3.8-27B-GGUF · Q4_K_M 22.7 GB / 24 GB
⚠️ Tight — reduce context
Qwen3.6-35B-A3B · fp16 85.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons