How much VRAM does HelpingAI 15B i1 need?

HelpingAI 15B i1 (15B parameters) requires approximately 14.3 GB of memory with Q4_K_M quantization.

What is the best quantization for HelpingAI 15B i1?

The recommended quantization for HelpingAI 15B i1 is Q4_K_M, which balances quality and memory efficiency.

Can it run?

Yes, RX 7600 XT 16GB can run HelpingAI 15B i1 with a C grade (Tight fit). Expected decode speed: 18.3 tok/s.

CUsable

Tight fit

Using Q4_K_M in Ollama

Capabilities:

Fit status

Tight fit

Decode

18.3 tok/s

TTFT

10605 ms

Safe context

18K

Memory

14.3 GB / 16.0 GB

Weights9.2 GB

KV Cache2.3 GB

Runtime1.2 GB

Headroom1.6 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Runs with offload (needs ~0.4 GB host RAM)	17.7 tok/s	15945 ms	31K
Chat	C	Tight fit	18.3 tok/s	5784 ms	10K
Coding	C	Tight fit	18.3 tok/s	10605 ms	18K
RAG	C	Runs with offload (needs ~0.4 GB host RAM)	17.7 tok/s	19931 ms	31K
Reasoning	C	Tight fit	22.7 tok/s	10096 ms

How HelpingAI 15B i1 (15B params) fits at each quantization level on RX 7600 XT 16GB (16.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	D37
Q3_K_S	3	7.4 GB	Low	D39
NVFP4	4

Upgrade options

MacBook Pro M4 32GBBudget pick

C9.4 tok/s decode

~$799 MSRP

RX 7900 XT 20GBBest value

C52.5 tok/s decode

~$899 MSRP