How much VRAM does Yi 1.5 6B Chat need?

Yi 1.5 6B Chat (6B parameters) requires approximately 6.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Yi 1.5 6B Chat?

The recommended quantization for Yi 1.5 6B Chat is Q4_K_M, which balances quality and memory efficiency.

Can it run?

Yes, RTX 2070 Super 8GB can run Yi 1.5 6B Chat with a C grade (Tight fit). Expected decode speed: 74.7 tok/s.

CUsable

Tight fit

Using Q4_K_M in Ollama

Capabilities:

Fit status

Tight fit

Decode

74.7 tok/s

TTFT

2593 ms

Safe context

19K

Memory

6.6 GB / 8.0 GB

Weights3.7 GB

KV Cache0.9 GB

Runtime1.2 GB

Headroom0.8 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Tight fit	88.1 tok/s	3195 ms	34K
Chat	B	Runs well	74.7 tok/s	1414 ms	10K
Coding	C	Tight fit	74.7 tok/s	2593 ms	19K
RAG	C	Tight fit	74.7 tok/s	4714 ms	34K
Reasoning	C	Tight fit	74.7 tok/s	3064 ms	19K

How Yi 1.5 6B Chat (6B params) fits at each quantization level on RTX 2070 Super 8GB (8.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.3 GB	Low	D35
Q3_K_S	3	2.9 GB	Low	D37
NVFP4	4

Upgrade options

RTX 3060 12GBBudget pick

C64.9 tok/s decode

~$329 MSRP

RX 7700 XT 12GBBest value

C70.8 tok/s decode

~$449 MSRP

RTX 3080 10GBBiggest leap

B157.8 tok/s decode

~$699 MSRP

RTX 2080 Ti 11GBNVIDIA upgrade