Qwen3.5-35B-A3B-APEX-GGUF
⚡ Each donation = another big MoE quantized I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant.If APEX quants are useful to you, your support directly funds those bigger runs. 🎉 Patreon (Monthly) &n...
Params
—
Context
—
Downloads 30d
208 K
Likes
94
Download history
daily snapshots · 29 days281 K179 K
Aug 24Sep 2Sep 12Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Qwen3.5-35B-A3B-APEX-I-Balanced.gguf | GGUF | 25.3 GB | 28.4 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run qwen3-5-35b-a3b-apex-gguf # pin the quantization explicitly $ ollama run qwen3-5-35b-a3b-apex-gguf-gguf
$ huggingface-cli download mudler/Qwen3.5-35B-A3B-APEX-GGUF-GGUF \
Qwen3.5-35B-A3B-APEX-I-Balanced.gguf --local-dir .
$ llama-cli -m Qwen3.5-35B-A3B-APEX-I-Balanced.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-5-35b-a3b-apex-gguf
{
"hf_id": "mudler/Qwen3.5-35B-A3B-APEX-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 208316,
"vram_estimates": [
{ "quant": "GGUF", "gb": 28.4 }
],
"updated_at": "2026-08-24T01:00:37Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-03-31
- Base model
- Qwen3.5-35B-A3B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-24
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model