ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com

LLM VRAM Calculator

Pick a model and a GPU to see weight + KV cache memory, estimated token speed, and ready-to-run launch commands.

Concurrency (Batch):
Dense 27B·64L (d=5120)·24Q/4KV·Ctx 256K·Text+Image+Video
Runnable Models →
GPUs
24 GB VRAM·1008 GB/s·Safe Usable 23.5 GB
Smooth Fit19.33 / 23.5 GB~42.6 tok/s
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Smooth Fit
19.33/ 23.5 GB usable

Physical 24 GB · Load 82.2%

Theoretical Decode Speed
~42.6tokens/s

Actual speed varies ~±25% by runtime

Max Context at Batch=1
78K/ 256K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 16.37 GBKV Cache (1×16K): 1.34 GBOverhead: 1.63 GB
🏃 Smooth & Snappy~11.7s for a 500-token response
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run qwen3.5:27b

RTX 4090 Fits Qwen3.5-27B · Cost & TCO

Approx. $1,899 (~$79/GB VRAM) · 450W TDP

Intelligence vs. Cost / VRAM Pareto Quadrant

Pareto Frontier

Top-left corner = maximum benchmark capability for minimum VRAM or API spend

↖ Sweet-Spot Value Zone8GB 卡16GB 甜点24GB (3090/4090)64GB (Mac/昇腾)128GB 主机512GB 顶配2233435464DeepSeek-V4-ProQwen3.5-122B-A10BQwen3.5-35B-A3BQwen3.5-27BQwen3-14BDeepSeek-R1-Distill-Qwen-7B
Qwen3.5-35B-A3BAlibaba Qwen · MoE A3BQ4: 23.34 GBIndex 45Pareto Optimal
Pareto China GlobalInspect →