Unverified50% confidenceBenchmarkExact time
On 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
VerifiedCalculated from a storage perspective: 27B parameters × 2 bytes (FP16) ≈ 54 GB, INT8 ≈ 27 GB, INT4 ≈ 13.5 GB, 2-bit ≈ 6.75 GB, 1.5-bit approaches 5 GB; fitting within 4 GB means the average bit width needs to be below 1.5-bit.77% 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.76% similarVerified以LLaMA-3 70B（80层、64头、每头128维）为例，单个token的KV Cache约占2.6MB（FP16精度），32K上下文的KV Cache总量约达83GB76% similarUnverifiedOllama local deployment measured throughput: MacBook M2 16GB approximately 15 tokens/second, RTX 3060 12GB approximately 45, RTX 4090 24GB approximately 70, 8GB laptop approximately 573% similarUnverifiedM3原始权重存储下限：BF16约854GB，8-bit约428GB，4-bit约214GB73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038323API
curl https://kongchang.com/api/v1/knowledge/claims/1038323MCP
get_claim(id=1038323)