Will It Run AI
CalculatorModelsHardwareCompare
Product
  • Calculator
  • Compare
  • Tier List
Browse
  • Models
  • Hardware
  • Docs
About
  • Why It Works
  • What's New
  • Legal Notice
  • Privacy Policy

All estimates are approximations based on mathematical models and public specifications. Actual performance may vary. Do not make purchasing decisions based solely on these estimates.

Data sourced from Hugging Face, Ollama, and official model documentation. Model names and logos are trademarks of their respective owners.

© 2026 Will It Run AI — Fase Consulting Ibiza, S.L. (NIF: B57969656)

Home/Qwen3.5 27B/on NVIDIA L40S 48GB

Can it run?

Can NVIDIA L40S 48GB run Qwen3.5 27B?

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

40.9 tok/s

TTFT

4731 ms

Safe context

29K

Memory

26.7 GB / 48.0 GB

Memory breakdown

Weights16.5 GB
KV Cache4.2 GB
Runtime1.2 GB
Headroom4.8 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well40.9 tok/s6882 ms50K
ChatCRuns well40.9 tok/s2581 ms16K
CodingCRuns well40.9 tok/s4731 ms29K
RAGCRuns well40.9 tok/s8603 ms50K
ReasoningCRuns well40.9 tok/s5592 ms29K

Quantization options

How Qwen3.5 27B (27B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
10.5 GB
LowD34
Q3_K_S
3
13.2 GB
LowD35
NVFP4
4
15.1 GB
MediumD36
Q4_K_M
4
16.5 GB
MediumD37
Q5_K_M
5
19.4 GB
HighD38
Q6_K
6
22.1 GB
HighD39
Q8_0Best for your GPU
8
28.9 GB
Very HighC42
F16
16
55.4 GB
MaximumF0

Get started

HuggingFace
huggingface-cli download hf-unsloth--qwen3-5-27b-gguf
See all results for NVIDIA L40S 48GBSee all hardware for Qwen3.5 27B