How much VRAM does Granite 3.1 MoE 1B FP16 need?

Granite 3.1 MoE 1B FP16 needs about 14GB minimum VRAM and 26GB optimal VRAM for a safer local run target.

Can Granite 3.1 MoE 1B FP16 run on an RTX 3090 24GB?

It may load on an RTX 3090 24GB because the minimum estimate is 14GB, but the safer target is 26GB. Expect tighter context or lower throughput.

What is the Ollama command for Granite 3.1 MoE 1B FP16?

Use ollama run granite3.1-moe:1b. Check the Ollama tag granite3.1-moe:1b before running.

What is the approximate Ollama model size for Granite 3.1 MoE 1B FP16?

Granite 3.1 MoE 1B FP16 uses the granite3.1-moe:1b Ollama tag. Treat the FP16 1 profile as smaller than the runtime VRAM budget; use 14GB minimum VRAM and 26GB optimal VRAM as the safer sizing numbers.

How much system RAM does Granite 3.1 MoE 1B FP16 need in Ollama?

Plan for at least 64GB system RAM alongside 14GB minimum VRAM and 26GB optimal VRAM. More RAM helps if layers spill to CPU or if you run multiple models.

What is the RAM vs VRAM requirement for Granite 3.1 MoE 1B FP16?

Granite 3.1 MoE 1B FP16 should be sized by GPU VRAM first: 14GB minimum and 26GB optimal. System RAM should be at least 64GB so Ollama has room for CPU-side layers, context, and the surrounding app process.

What is Granite 3.1 MoE 1B FP16 VRAM usage on an RTX 3090?

Granite 3.1 MoE 1B FP16 is borderline for an RTX 3090 24GB target. The page estimates 14GB minimum and 26GB optimal VRAM, with spill risk marked as high without a larger GPU or cloud.

Which LocalVRAM profiles share the granite3.1-moe:1b Ollama tag?

LocalVRAM tracks these profiles for the same Ollama tag or model family: Granite 3.1 MoE 1B FP16 (FP16, 14GB min/26GB optimal); Granite 3.1 MoE 1B Q4 (Q4, 2GB min/12GB optimal); Granite 3.1 MoE 1B Q5 (Q5, 4GB min/14GB optimal); Granite 3.1 MoE 1B Q8 (Q8, 8GB min/18GB optimal). Use the table on this page to compare quantization and VRAM targets before choosing a run command.

Is Granite 3.1 MoE 1B FP16 benchmark data measured or estimated?

Granite 3.1 MoE 1B FP16 currently uses estimated baseline anchors on this page. Verified benchmark data will replace the estimate after a local hardware run is available.

Granite 3.1 MoE 1B FP16 VRAM Requirement and Ollama Model Size

Granite 3.1 MoE 1B FP16 needs 14GB minimum VRAM, 26GB optimal VRAM, and 64GB+ system RAM for a safer Ollama run. Popular Ollama model family: Granite 3.1 MoE. Caveat: Estimated values are placeholders unless marked measured..

Hardware Snapshot

Family	Granite 3.1 MoE
Scenario	reasoning
License scope	open-source
Quantization	FP16
VRAM minimum	14GB
VRAM optimal	26GB
Best local GPU	RTX 6000 Ada 48GB
Cloud fallback	A100 80GB
Updated	2026-02-24
Data status	Estimated baseline (pending measurement)
Ollama source	Library reference (verified: 2026-02-24)
Ollama tag	`granite3.1-moe:1b`
Category	reasoning

Benchmark Anchors

Hardware	Expected tok/s
RTX 3090 24GB	26.4
RTX 4090 24GB	35.6
A100 80GB	63.4

Quick Answers

How much VRAM does Granite 3.1 MoE 1B FP16 need?: Granite 3.1 MoE 1B FP16 needs about 14GB minimum VRAM and 26GB optimal VRAM for a safer local run target.
Can Granite 3.1 MoE 1B FP16 run on an RTX 3090 24GB?: It may load on an RTX 3090 24GB because the minimum estimate is 14GB, but the safer target is 26GB. Expect tighter context or lower throughput.
What is the Ollama command for Granite 3.1 MoE 1B FP16?: Use ollama run granite3.1-moe:1b. Check the Ollama tag granite3.1-moe:1b before running.
What is the approximate Ollama model size for Granite 3.1 MoE 1B FP16?: Granite 3.1 MoE 1B FP16 uses the granite3.1-moe:1b Ollama tag. Treat the FP16 1 profile as smaller than the runtime VRAM budget; use 14GB minimum VRAM and 26GB optimal VRAM as the safer sizing numbers.
How much system RAM does Granite 3.1 MoE 1B FP16 need in Ollama?: Plan for at least 64GB system RAM alongside 14GB minimum VRAM and 26GB optimal VRAM. More RAM helps if layers spill to CPU or if you run multiple models.
What is the RAM vs VRAM requirement for Granite 3.1 MoE 1B FP16?: Granite 3.1 MoE 1B FP16 should be sized by GPU VRAM first: 14GB minimum and 26GB optimal. System RAM should be at least 64GB so Ollama has room for CPU-side layers, context, and the surrounding app process.
What is Granite 3.1 MoE 1B FP16 VRAM usage on an RTX 3090?: Granite 3.1 MoE 1B FP16 is borderline for an RTX 3090 24GB target. The page estimates 14GB minimum and 26GB optimal VRAM, with spill risk marked as high without a larger GPU or cloud.
Which LocalVRAM profiles share the granite3.1-moe:1b Ollama tag?: LocalVRAM tracks these profiles for the same Ollama tag or model family: Granite 3.1 MoE 1B FP16 (FP16, 14GB min/26GB optimal); Granite 3.1 MoE 1B Q4 (Q4, 2GB min/12GB optimal); Granite 3.1 MoE 1B Q5 (Q5, 4GB min/14GB optimal); Granite 3.1 MoE 1B Q8 (Q8, 8GB min/18GB optimal). Use the table on this page to compare quantization and VRAM targets before choosing a run command.
Is Granite 3.1 MoE 1B FP16 benchmark data measured or estimated?: Granite 3.1 MoE 1B FP16 currently uses estimated baseline anchors on this page. Verified benchmark data will replace the estimate after a local hardware run is available.

Ollama Model Size and RAM Notes

Ollama tag	`granite3.1-moe:1b`
Run command	`ollama run granite3.1-moe:1b`
Model size guidance	FP16 quantization, 1 profile; size runtime by VRAM, not download size alone
Runtime VRAM target	14GB minimum, 26GB optimal
System RAM planning	64GB or more when running this tag locally with Ollama

Download size alone is not a safe runtime budget. Runtime memory also includes KV cache, context length, and GPU layer placement.

Ollama RAM vs VRAM Requirements

GPU VRAM usage estimate	14GB minimum / 26GB optimal
System RAM requirement	64GB or more for Ollama runtime headroom
RTX 3090 24GB fit	Borderline
CPU spill risk	High without larger GPU or cloud
Context warning	Longer context increases KV cache memory, so real VRAM usage can exceed short-prompt estimates.

For Ollama, VRAM is the first fit check. System RAM matters when layers spill to CPU, when context grows, or when the local app stack runs beside the model.

Available Tag Variants and VRAM Targets

Profile	Quantization	VRAM target	Ollama tag
Granite 3.1 MoE 1B FP16	FP16	14GB min / 26GB optimal	`granite3.1-moe:1b`
Granite 3.1 MoE 1B Q4	Q4	2GB min / 12GB optimal	`granite3.1-moe:1b`
Granite 3.1 MoE 1B Q5	Q5	4GB min / 14GB optimal	`granite3.1-moe:1b`
Granite 3.1 MoE 1B Q8	Q8	8GB min / 18GB optimal	`granite3.1-moe:1b`

Ollama library tags often group multiple quantization choices under one model family. LocalVRAM separates them into VRAM profiles so you can pick the right local target.

Real Hardware Benchmark (RTX 3090)

Real benchmark data not available yet for this tag. Estimated anchors are shown above.

Performance Curve

Reference anchors are baseline estimates. Measured RTX 3090 data is overlaid when available.

Best Hardware for Granite 3.1 MoE 1B FP16

Local run: RTX 3090 (24GB) (Check latest deal) for around 26.4 tok/s on this profile.
Cloud run: RunPod A100 80GB , about 2.4x the local 3090 speed anchor.
Alternative cloud: Vast.ai options for flexible spot pricing.

Local vs Cloud Cost Hint

Mode	40h / month	120h / month
Local power only (3090 baseline)	$2.24	$6.72
A100 80GB	$78	$234

Related Model Profiles

Granite 3.1 MoE 1B Q4 2GB min, 12GB optimal
Granite 3.1 MoE 1B Q5 4GB min, 14GB optimal
Granite 3.1 MoE 1B Q8 8GB min, 18GB optimal

ollama run granite3.1-moe:1b More reasoning models More tiny-class models Benchmark changelog Submit your test result Run on RunPod Try Vast.ai

We may earn a commission if you click links on this page.

This page currently uses estimated benchmark baselines. Measured data will replace it after validation.