unsloth / text-generation updated 1 month ago

Qwen-AgentWorld-35B-A3B-GGUF

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

Params
Context
Downloads 30d
534 K
Likes
221
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 10 days
673 K534 K
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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Qwen-AgentWorld-35B-A3B-UD-IQ2_XXS.gguf IQ2_XXS 11.5 GB 13.1 GB ✅ Runs comfortably
Qwen-AgentWorld-35B-A3B-UD-IQ2_M.gguf IQ2_M 11.6 GB 13.2 GB ✅ Runs comfortably
Qwen-AgentWorld-35B-A3B-UD-IQ3_XXS.gguf IQ3_XXS 13.7 GB 15.6 GB ✅ Runs comfortably
Qwen-AgentWorld-35B-A3B-UD-IQ3_S.gguf IQ3_S 15.0 GB 17.0 GB ✅ Runs comfortably
Qwen-AgentWorld-35B-A3B-UD-IQ4_XS.gguf IQ4_XS 17.8 GB 20.1 GB ⚠️ Tight — reduce context
Qwen-AgentWorld-35B-A3B-UD-IQ4_NL.gguf IQ4_NL 18.1 GB 20.4 GB ⚠️ Tight — reduce context
Qwen-AgentWorld-35B-A3B-Q8_0.gguf Q8_0 36.9 GB 41.1 GB ❌ Won’t fit
Qwen-AgentWorld-35B-A3B-BF16-00001-of-00002.gguf GGUF 49.8 GB 55.3 GB ❌ Won’t fit
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 · GGUF
$ ollama run qwen-agentworld-35b-a3b-gguf

# pin the quantization explicitly
$ ollama run qwen-agentworld-35b-a3b-gguf-gguf
est. VRAM 55.3 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2026-06-24
Training datasets
Qwen/AgentWorldBench
Added to our catalog
2026-07-28
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.