Unverified50% confidenceDecision RuleExact time
When using Strata to run Kunon 3.8 FlashNext, it is recommended to use the IQ2 or IQ3 quantization level, prepare 48GB to 64GB of system memory, and leave 70GB to 80GB of NVMe SSD space.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Running 125B MoE on a 12GB GPU? Inside Strata's Three-Tier Cooperative Engine
bilibiliNicksxs11/3/2026
Related Entities
Related Claims
UnverifiedStrata offers multiple quantization tiers: 66GB Q20 (fastest), 68GB IQ2XS (balanced), 76GB IQ3XS (best quality), with the test using IQ3S at 83.6GB.77% similarUnverifiedThe Qwen3.8 Flash Next (Q3 quantized version) weights are approximately 84 GB and run on an AMD 7900XTX 24 GB GPU with an average decoding output speed of approximately 90 tokens/s.74% similarUnverifiedStrata's IQ3_XXS quantization version compresses expert weights to approximately 3 bits, with the experts alone occupying approximately 43 GB of memory.73% similarUnverifiedStrata enables a single GPU with 12 GB of VRAM to smoothly run Qwen3.8 Flash Next, a large model with 125 billion activated parameters and an overall size of 176B.69% similarVerifiedMemory requirements are at least 37.6 GB for Q2_0, at least 39.2 GB for IQ2_XS, and at least 47 GB for IQ3_XXS, with the vision encoder occupying an additional 0.91 GB.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134850API
curl https://kongchang.com/api/v1/knowledge/claims/1134850MCP
get_claim(id=1134850)