How much VRAM does Qwen3.5 122B need at Q4_K_M? The 2026 MoE workhorse
Qwen3.5 122B at 104 GB resident is the configuration to deploy when you have datacenter-grade hardware and want frontier reasoning quality with Apache 2.0 licensing. On a smaller GPU you can move expert weights to system RAM, but the host then has to hold them and every token gets slower.
Qwen3.5 122B at Q4_K_M with native 256K context needs about 104 GB of VRAM with all 122B params resident. The architecture is Qwen's Gated Delta Networks at scale: 48 layers, 12B active per token, 2 KV heads, head_dim 256, native 256K context. It's the workhorse MoE of the 2026 Qwen3.5 fleet - frontier-quality reasoning with Apache 2.0 licensing. Those 12B active params don't shrink what has to stay loaded, because different tokens pick different experts.
By TechCompare · Updated
Calculator
Estimated VRAM required
103 GB
122B params at Q4_K_M, 262,144 token context, batch 1, inference.
Estimate accuracy: Weights within ~2%. KV cache within ~5% for standard GQA models, ~10% for MLA or hybrid state estimates. Real VRAM may vary with framework (vLLM vs llama.cpp vs Transformers), Flash Attention, and driver overhead.
Custom architecture - SWA not applied. If you're modeling Gemma 3/4 or Mistral Nemo, pick the preset for accurate KV cache.
Hardware that fits
Apple entries show installed unified memory separately from a model budget based on an 8 GB reserve. That budget is a planning heuristic, not a fixed hardware limit.
Just barely too small
How this is calculated
68 GB of weights at Q4_K_M, 26 GB KV cache (at the full 256K native context), and ~9.4 GB overhead. The 104 GB resident total is the deployment number - one H200 141GB, an MI300X, or two 80 GB cards with tensor parallelism.
Verdict
The arithmetic adds cleanly: 68 GB of Q4 weights, 26 GB of FP16 KV cache at the full 256K context, and 9.4 GB of overhead totaling 104 GB resident. Resident fits a single H200 141GB or MI300X, or two 80 GB cards with tensor parallelism. The 12B active count doesn't lower the resident total, because any token can route to any expert. Qwen3.5's Gated Delta Networks add a constant-memory layer path on top of the Gated standard-attention path, so the actual long-context behavior is even better than what the calculator's 26 GB cache suggests.
More Qwen scenarios
Related guides
Frequently asked questions
How does Qwen3.5 122B compare to Llama 4 Scout?
What about Qwen3.5 27B (dense) instead?
Does Qwen3.5 use Gated Delta Networks?
Related tools
RAM Latency Calculator
Convert DDR3/DDR4/DDR5 timings (CL, tRCD, tRP, tRAS) into true latency in nanoseconds.
Use tool ➜Power Cost Estimator
Estimate annual electricity costs for your PC, Server, or TV.
Use tool ➜Data Transfer Calculator
Estimate transfer times for files over USB, WiFi, Ethernet, and more.
Use tool ➜Memory and Storage Throughput Visualizer
Visualize the massive speed difference between CPU cache, RAM, and storage.
Use tool ➜