Survival LLM runs an offline emergency assistant on a local PC
It picks among Nemotron, Qwen and Granite models by memory and cites FEMA, CDC and other local sources.
24
AI model
Qwen3.8 27B
- Mentions · 7d0
- Mentions · 30d1
- All mentions4
- First seenSep 8, 2026
- Last mentioned15d ago
Timeline
4 articles · newest firstPrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model Retaining 98.2% of Qwen3.8 27B Performance
PrismML released Ternary Bonsai 2 27B, a 5.93 GB Apache 2.0 ternary-weight model retaining 98.2% of Qwen3.8 27B's benchmark performance.
58
PrismML hopes its tiny LLM will change how we all use AI
PrismML released Bonsai 2 27B, compressing Alibaba's Qwen 27B to 5.9 GB with ternary weights while retaining 98% of benchmark performance.
48
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
Quesma benchmarks Qwen3.8 27B quantizations: 4-bit Q4_K_M matches BF16 on key benchmarks while 1-bit collapses to random chance.
55
Appears with
- PrismMLvendor · 2
- llama.cppproduct · 2
- Qwen3.8 27Bproduct · 2
- FEMAorganization · 1
- NVIDIA Nemotron 3.5 Lightningai model · 1
- NVIDIA Nemotron 3.5 Superai model · 1
- Appleorganization · 1
- IBMvendor · 1
- Unslothorganization · 1
- Cerberus Capitalorganization · 1
- Bonsai 2 27Bai model · 1
- MLXproduct · 1
- IBM Granite 4.2 8Bai model · 1
- Quesmavendor · 1
- PrismMLorganization · 1
- Ternary Bonsai 2 27Bai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.