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/Pixtral Large 124B/on H100 NVL 188GB

Can it run?

Can H100 NVL 188GB run Pixtral Large 124B?

BGood

Runs well

Using Q4_K_M in vLLM

Capabilities:

Fit status

Runs well

Decode

83.5 tok/s

TTFT

2318 ms

Safe context

26K

Memory

116.2 GB / 188.0 GB

Memory breakdown

Weights75.6 GB
KV Cache19.4 GB
Runtime2.4 GB
Headroom18.8 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingBRuns well83.5 tok/s3371 ms44K
ChatCRuns well83.5 tok/s1264 ms14K
CodingBRuns well83.5 tok/s2318 ms26K
RAGBRuns well83.5 tok/s4214 ms44K
ReasoningBRuns well83.5 tok/s2739 ms26K

Quantization options

How Pixtral Large 124B (124B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
48.4 GB
LowD35
Q3_K_S
3
60.8 GB
LowD36
NVFP4
4
69.4 GB
MediumD37
Q4_K_M
4
75.6 GB
MediumD38
Q5_K_M
5
89.3 GB
HighD40
Q6_K
6
101.7 GB
HighC41
Q8_0Best for your GPU
8
132.7 GB
Very HighC44
F16
16
254.2 GB
MaximumF0

Get started

HuggingFace
huggingface-cli download pixtral-large-124b
See all results for H100 NVL 188GBSee all hardware for Pixtral Large 124B