How much VRAM does Mistral Small 4 119B need?

Mistral Small 4 119B (119B parameters) requires approximately 86.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Mistral Small 4 119B?

The recommended quantization for Mistral Small 4 119B is Q4_K_M, which balances quality and memory efficiency.

Can it run?

No, Mistral Small 4 119B requires more memory than MacBook Pro M4 Max 96GB provides.

FWon't run

Too heavy

Using Q4_K_M in vLLM

Capabilities:

Fit status

Too heavy

Decode

14.2 tok/s

TTFT

13610 ms

Safe context

13K

Memory

86.4 GB / 69.1 GB

Weights72.6 GB

KV Cache1.0 GB

Runtime2.4 GB

Headroom10.4 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	F	Too heavy	13.8 tok/s	20425 ms	25K
Chat	F	Too heavy	13.8 tok/s	7659 ms	6K
Coding	F	Too heavy	14.2 tok/s	13610 ms	13K
RAG	F	Too heavy	13.8 tok/s	25531 ms	25K
Reasoning	F	Too heavy	13.8 tok/s	16595 ms	13K

How Mistral Small 4 119B (119B params) fits at each quantization level on MacBook Pro M4 Max 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_KBest for your GPU	2	46.4 GB	Low	C44
Q3_K_S	3	58.3 GB	Low	C45

Upgrade options

MacBook Pro M3 Max 128GBBest value

C9.6 tok/s decode

~$2,499 MSRP

AMD Instinct MI350X 288GBBudget pick

C234.1 tok/s decode

~$8,000 MSRP

Gaudi 3 128GBBiggest leap