AMD Radeon(TM) Graphics | VRAM Check Result

Leaderboard result

247.1tok/sCanonical score

ClassB

Public class

Placed #9 / 27 globally under the canonical benchmark profile.

Best used as a baseline before larger local AI targets.

AMD Radeon(TM) Graphics

ModelTinyLlama 1.1B (Q4_K_M)

QuantQ4_K_M

DateApr 30, 2026

Global standingPublic leaderboard position

Global#9/ 27 Cohort#1/ 1 Country#5/ 8

Workload & profileMeasured benchmark configuration

ModelTinyLlama 1.1B (Q4_K_M)

MethodQ4_K_M

ProfileCanonical profile

Recommended workloadsCurrent envelope is still tight

Base inference only

Use the sections below if you want the full fit matrix and planner-backed next step.

Details & explanationContext and scoring rules

Run meaningOfficial scored run

This run sets an official score, class, and public ranking under the canonical benchmark profile.

Trust & system contextVerified GPU (Leaderboard Eligible)

This is the canonical number the leaderboard uses for this run.

vulkan backendDiscrete GPU memoryFirst limit: Memory headroom

Step 01

Measured output

The official score plus the few supporting numbers that explain how this run behaved.

Decode ThroughputScored pass

247.1tok/s

This is the canonical number the leaderboard uses for this run.

ProfileTinyLlama 1.1B (Q4_K_M)

Standing#9 / 27 global

Prefill throughput

11232.9 tok/s

TTFT p50

5 ms

Effective model memory

0.0 GB

Scored pass duration

Stability rangeDecode / TTFT

0.32% / 6.47%

Step 02

What this run supports

This is the plain-language support map for the current build: what runs well now, what is close, and what still needs bigger hardware.

Ready nowNo strong lane yet

This workload still needs more memory or speed before it becomes practical.

Base inference only

Closest stretchNothing is one small step away

The current build already covers the best near-term lanes, so there is no obvious single stretch target.

No clear stretch lane

Still outside envelopeCoding · General chat · Math / reasoning · Embeddings

These workloads still need more memory or speed than this machine can comfortably provide.

CodingGeneral chatMath / reasoningEmbeddings

Using the local model catalog for this guidance.

CodingNot a good fit yet

No strong fits in the tracked set yet

Works well nowCoding still needs more hardware

This workload still needs more memory or speed before it becomes practical.

What more headroom changesA targeted upgrade opens more options

The clearest next unlocks are Granite Code 3B · StarCoder2 3B · Qwen3 4B Instruct.

Main limit under reviewBased on local model catalog

General chatNot a good fit yet

No strong fits in the tracked set yet

Works well nowGeneral chat still needs more hardware

This workload still needs more memory or speed before it becomes practical.

What more headroom changesA targeted upgrade opens more options

The clearest next unlocks are Llama 3.2 1B Instruct · TinyLlama 1.1B · Falcon3 1B Instruct.

Main limit under reviewBased on local model catalog

Math / reasoningNot a good fit yet

No strong fits in the tracked set yet

Works well nowMath / reasoning still needs more hardware

This workload still needs more memory or speed before it becomes practical.

What more headroom changesA targeted upgrade opens more options

The clearest next unlocks are Llama 3.2 1B Instruct · TinyLlama 1.1B · Falcon3 1B Instruct.

Main limit under reviewBased on local model catalog

EmbeddingsNot a good fit yet

No strong fits in the tracked set yet

Works well nowEmbeddings still needs more hardware

This workload still needs more memory or speed before it becomes practical.

What more headroom changesA targeted upgrade opens more options

The clearest next unlocks are all-minilm · Nomic Embed Text v1.5 · mxbai-embed-large.

Main limit under reviewBased on local model catalog

Step 03

Primary constraint

This is the clearest limit in the current build, how we know it, and why the recommendation points there.

Primary constraintMemory is the first thing this build runs out of

This run had 0.0 GB of effective model memory. That is enough for smaller local AI workloads, but larger coding and reasoning models run out of room before raw speed becomes the problem.

What hits first0.0 GB effective model memory

Bigger coding and reasoning families run out of room before speed becomes the main issue.

What still worksThis build is best used for smaller local AI targets

Smaller local AI workloads are already comfortable on this build today.

Why we recommend thisPrioritize more memory headroom

That is the fastest way to move from smaller models to larger ones without changing the whole character of the build.

Why this recommendationMore memory headroom unlocks the next tier of models

That is why the recommendation points to more memory headroom first. It unlocks larger model families sooner than chasing speed alone.

Coding · General chat · Math / reasoning · EmbeddingsStep 04 is still rebuilding the ladder from the measured envelope of this run.

Trust and system context

Compact evidence behind why this run should be believed and how the machine was identified.

Execution profileVerified GPU benchmark

Validation statusVerified

Run qualityStable

Methodologyv1.1

GPUAMD Radeon(TM) Graphics

CPUAMD Ryzen 5 7640HS w/ Radeon 760M Graphics

VRAM / RAM0.4 / 31.3 GB

OSWindows 11 24H2 (Build 26200)

Client version0.1.0

DriverNot reported

Step 04

GPU upgrade stage

A build-relative ladder that stays practical first, then shows the sweet spot, then the aspirational ceiling.

Detected bottleneckMemory is the first thing this build runs out of

That is why the recommendation points to more memory headroom first. It unlocks larger model families sooner than chasing speed alone.

Minimum acceptableUpgrade ladder is loading

Hardware path

Current buildHold

Using the current build as the temporary baseline

Why this tierBudget-conscious jump

Choose this if you want the lowest-cost GPU jump that still changes what the build can realistically run.

What it opensThe full ladder appears as soon as model guidance finishes loading

VRAM Check is rebuilding the ladder from the measured envelope of this run.

Open methodology

RecommendedUpgrade ladder is loading

Hardware pathDefault choice

Current buildHold

Using the current build as the temporary baseline

Why this tierBest long-term value

Choose this if you want the strongest day-to-day value. It is the most balanced step for real gains without jumping straight into premium pricing.

What it opensThe full ladder appears as soon as model guidance finishes loading

VRAM Check is rebuilding the ladder from the measured envelope of this run.

Open methodology

Top endUpgrade ladder is loading

Hardware path

Current buildHold

Using the current build as the temporary baseline

Why this tierPeak consumer path

Choose this only if budget is flexible and you want the highest normal consumer ceiling, not the best value per dollar.

What it opensThe full ladder appears as soon as model guidance finishes loading

VRAM Check is rebuilding the ladder from the measured envelope of this run.

Open methodology

Keep this result movingCompare this build on the leaderboard or share the result without losing context.

See leaderboard context Share result

Optional depth

Planner, catalog, and audit trail

The report above stays focused on the outcome. Open this workspace when you want to compare model families, browse the tracked catalog, or inspect the pass evidence behind the score.

Open this only when you need the deeper planning layer

0% of tracked coding fits clear on this machine today.