RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata
A Strata-ready repackaging of 0bserverx/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-GGUF (IQ3S quant family): 1. RVN-Qwen3.8-Flash-Next-IQ3S-merged.gguf — the original 8-shard split GGUF merged into a single file (83 GiB), ready to feed directly to a Strata native pack. 2. pack/ — a pre-built Strata pack (from the same version of iqpack.py --compat-bf16 shipped in Strata 0.1.30). Point --pack at it and Strata reads...
Params
—
Context
—
Downloads 30d
352 K
Likes
27
Download history
daily snapshots · 15 days352 K178 K
Oct 10Oct 15Oct 20Oct 24
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 |
|---|---|---|---|---|
| RVN-Qwen3.8-Flash-Next-IQ3_S-merged.gguf | IQ3_S | 88.9 GB | 98.3 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 run rvn-qwen3-8-flash-next-abliterated-uncensored-iq3-s-strata # pin the quantization explicitly $ ollama run rvn-qwen3-8-flash-next-abliterated-uncensored-iq3-s-strata-iq3_s
$ huggingface-cli download jimmy31chen/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata-GGUF \
RVN-Qwen3.8-Flash-Next-IQ3_S-merged.gguf --local-dir .
$ llama-cli -m RVN-Qwen3.8-Flash-Next-IQ3_S-merged.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/rvn-qwen3-8-flash-next-abliterated-uncensored-iq3-s-strata
{
"hf_id": "jimmy31chen/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 352158,
"vram_estimates": [
{ "quant": "IQ3_S", "gb": 98.3 }
],
"updated_at": "2026-10-10T01:00:13Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-01
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-10
Compare with any text-generation model
Appears in