Skip to content
Run LLM Locally

Qwen3.5 122B-A10B on the RTX 4080

Qwen3.5 122B-A10B at Q4_K_M needs about 76.2 GB: the RTX 4080 (16 GB) cannot run it well, even with system RAM. At Q3_K_M it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Qwen3.5 122B-A10B

Q4_K_M · 8K context

Incompatible

The model needs about 76.2 GB; VRAM plus usable RAM give 66.7 GB. 9.5 GB are missing.

Your hardware
RTX 4080 16 GB · 64 GB RAM
Estimated memory
~76.2 GB estimate
VRAM (usable memory)
15.5 GB
GPU only
No
CPU/GPU offload
Required (51.2 GB)
Generation speed
Not available
Largest context in fast memory
None
Confidence: high

Memory breakdown

~76.2 GB (74.3 GB–78.1 GB) needed · estimate

Does not fit · 9.5 GB missing

  • Model weights71.3 GB
  • KV cache0.3 GB
  • Runtime overhead1 GB
  • Safety margin3.6 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size

EstimateData updated 40 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • split CPU/GPU runs vary a lot with the CPU and PCIe link
  • system RAM speed unknown (dual-channel DDR4-3200 assumed)
  • mixture-of-experts: speed depends on expert routing

Other quantizations on the RTX 4080

Qwen3.5 122B-A10B on RTX 4080 + 64 GB RAM · 8K context
Qwen3.5 122B-A10B Q8_08K~128 GB · No dataIncompatible
Qwen3.5 122B-A10B Q6_K8K~100 GB · No dataIncompatible
Qwen3.5 122B-A10B Q5_K_M8K~90.9 GB · No dataIncompatible
Qwen3.5 122B-A10B Q4_K_M8K~76.2 GB · No dataIncompatible
Qwen3.5 122B-A10B IQ4_XS8K~69.6 GB · No dataIncompatible
Qwen3.5 122B-A10B Q3_K_M8K~56.5 GB · 5.5–11 tok/s estimatePossible but slow

Alternatives

GPUs that run Qwen3.5 122B-A10B Q4_K_M entirely in VRAM

Other models that fit the RTX 4080

Hardware that runs Qwen3.5 122B-A10B Q4_K_M entirely in memory

Prices and links follow the market you choose.

RTX PRO 6000 Blackwell Workstation Edition

NVIDIA

ExcellentRuns Qwen3.5 122B-A10B Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

Radeon PRO W7900

AMD

ExcellentRuns Qwen3.5 122B-A10B Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

NVIDIA DGX Spark (GB10)

Unified memory PC

ExcellentRuns Qwen3.5 122B-A10B Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the RTX 4080 run Qwen3.5 122B-A10B?
The model needs about 76.2 GB; VRAM plus usable RAM give 66.7 GB. 9.5 GB are missing.
Which quantization should I use on the RTX 4080?
None fits entirely in VRAM at 8K context; the smallest, Q3_K_M, still needs offload.
What is the largest context on the RTX 4080?
At Q4_K_M, the model does not fit entirely in VRAM even at a short context.