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
Q4_K_M: Out of VRAM (OOM) 77.26 GB / 23.5 GB Usable

Qwen3.5-122B-A10B (MoE) on NVIDIA GeForce RTX 3090 24GB: VRAM Requirement & Speed Estimate

A single RTX 3090 (23.5 GB usable VRAM) cannot fully fit Qwen3.5-122B-A10B (MoE) at Q4_K_M (77.26 GB required). Consider multi-GPU tensor parallelism, a smaller parameter variant, or cloud GPU / API deployment.

Concurrency (Batch):
MoE 122B / A10B·48L (d=3072)·32Q/2KV·Ctx 256K·Text+Image+Video
Runnable Models →
GPUs
24 GB VRAM·936 GB/s·Safe Usable 23.5 GB
Out of VRAM (OOM)77.26 / 23.5 GBOOM
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Out of VRAM (OOM)
77.26/ 23.5 GB usable

Physical 24 GB · Load 328.5%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 53.74 GB

Max Context at Batch=1
0K/ 256K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 73.96 GBKV Cache (1×16K): 0.52 GBOverhead: 2.78 GB
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run qwen3.5:122b-a10b

Insufficient Local VRAM? Ways to Run Qwen3.5-122B-A10B (MoE)

Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.

📊 All Quantization Levels for Qwen3.5-122B-A10B (MoE) on RTX 3090

Quantization Total VRAM (16K) Verdict Est. Speed Max Context
FP16 / BF16 250.7 GB Out of VRAM (OOM) — —
FP8 / Q8_0 134.04 GB Out of VRAM (OOM) — —
GGUF Q6_K 103.86 GB Out of VRAM (OOM) — —
GGUF Q5_K_M 90.33 GB Out of VRAM (OOM) — —
Q4_K_M / AWQ 77.26 GB Out of VRAM (OOM) — —
GGUF IQ4_XS 67.93 GB Out of VRAM (OOM) — —
GGUF Q3_K_M 62.64 GB Out of VRAM (OOM) — —
GGUF Q2_K 50.82 GB Out of VRAM (OOM) — —

💡 Recommended Alternative GPUs & Macs for Qwen3.5-122B-A10B (MoE)

Frequently Asked Questions

Can NVIDIA GeForce RTX 3090 24GB run Qwen3.5-122B-A10B (MoE) locally?

A single RTX 3090 (23.5 GB usable VRAM) cannot fully fit Qwen3.5-122B-A10B (MoE) at Q4_K_M (77.26 GB required). Consider multi-GPU tensor parallelism, a smaller parameter variant, or cloud GPU / API deployment.

What is the best quantization for Qwen3.5-122B-A10B (MoE) on RTX 3090?

Qwen3.5-122B-A10B (MoE) (122B parameters) exceeds single-device VRAM even at aggressive 2–3 bit quantization. Cloud GPUs or hosted APIs are recommended.

How much VRAM does Qwen3.5-122B-A10B (MoE) need in full FP16 precision?

In unquantized FP16/BF16 precision (16K context), Qwen3.5-122B-A10B (MoE) requires 250.7 GB VRAM (244 GB for weights alone). Because it uses a Mixture-of-Experts (MoE) architecture, all 122B parameters must sit in memory, while only 10B active parameters are read per token.