Unverified50% confidenceFactExact time
The blogger koustubh runs the 4-bit GGUF quantized version (UD-IQ4_NL) of Qwen3.5-122B-A10B on a Mac Studio, actually occupying about 62GB of memory.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedThe 1-bit Dynamic GGUF version of Qwen3.8-Flash-Next can run on 75 GB of memory or unified memory, reducing the size by 79% compared to the original BF16 format while retaining 80% of top-1 accuracy.77% similarUnverifiedEarly versions of Hishob ran on a 6GB mini PC using a small 3B model; the hardware was later upgraded to a Mac Studio (M3 Ultra, 96GB unified memory) running the Qwen3.5-122B-A10B model locally.77% similarUnverifiedOn a single Mac Studio with 512GB of memory, the 128B Mistral Medium 3.5 (FP8) and the 27B Qwen 3.8 (BF16) occupy about 158GB and 68GB of memory respectively at a 65536-token context.74% similarUnverifiedqwen/qwen3.6-35b-a3b is a MoE (mixture-of-experts) model in the Qwen series, and of its 35B parameters only about 3B are activated per token, so it can run at over 100 tok/s on unified-memory devices such as a Mac Studio.73% similarVerifiedAfter 4-bit quantization, Llama 3.3 70B has a model size of approximately 40 GB and can run on a Mac Studio with 64 GB of memory or a single professional GPU with 48 GB of VRAM.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059166API
curl https://kongchang.com/api/v1/knowledge/claims/1059166MCP
get_claim(id=1059166)