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/Mistral Small 4 119B/on NVIDIA H200 141GB

Can it run?

Can NVIDIA H200 141GB run Mistral Small 4 119B?

BGood

Runs well

Using Q4_K_M in vLLM

Capabilities:

Fit status

Runs well

Decode

161.6 tok/s

TTFT

1198 ms

Safe context

25K

Memory

90.1 GB / 141.0 GB

Memory breakdown

Weights72.6 GB
KV Cache1.0 GB
Runtime2.4 GB
Headroom14.1 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingBRuns well161.6 tok/s1742 ms50K
ChatBRuns well161.6 tok/s653 ms13K
CodingBRuns well161.6 tok/s1198 ms25K
RAGBRuns well161.6 tok/s2178 ms50K
ReasoningBRuns well161.6 tok/s1416 ms25K

Quantization options

How Mistral Small 4 119B (119B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
46.4 GB
LowD37
Q3_K_S
3
58.3 GB
LowD38
NVFP4
4
66.6 GB
MediumD40
Q4_K_M
4
72.6 GB
MediumC41
Q5_K_M
5
85.7 GB
HighC43
Q6_KBest for your GPU
6
97.6 GB
HighC44
Q8_0
8
127.3 GB
Very HighC45
F16
16
244.0 GB
MaximumF0

Get started

HuggingFace
huggingface-cli download mistral-small-4-119b
See all results for NVIDIA H200 141GBSee all hardware for Mistral Small 4 119B