Will It Run AI

Can Falcon H1 Tiny 90M Instruct run on RX 6800 16GB?

YES — Runs Great

D34Poor
Estimated from fit model

Falcon H1 Tiny 90M Instruct needs ~2.7 GB VRAM. RX 6800 16GB has 16.0 GB. With Q4_K_M quantization, expect ~2 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: StandardBottleneck: Memory bandwidth
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 2.7 GB, 2.0 tok/s, Runs well
2.7 GB required16.0 GB available
17% VRAM used

Fit status

Runs well

Decode

2.0 tok/s

TTFT

96800 ms

Safe context

2.2M

Memory

2.7 GB / 16.0 GB

Memory breakdown

Weights0.1 GB
KV Cache0.1 GB
Runtime0.9 GB
Headroom1.6 GB

See how fast it feels

See how fast it feelsFalcon H1 Tiny 90M Instruct on RX 6800 16GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 2.0 tok/s decode · 96.8s TTFT (warm) · 5 tok/s prefill

What limits this setup

This model fits, but memory bandwidth is the part holding decode speed back.

Throughput will feel slow

Estimated decode speed is only 2.0 tok/s, so this is more of a technical fit than a comfortable daily-driver setup.

Best improvement path

Prioritize bandwidth, not only capacity

If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatDRuns well2.0 tok/s52800 ms1.1M
CodingDRuns well2.0 tok/s96800 ms2.2M
Agentic CodingDRuns well2.0 tok/s140800 ms4.3M
ReasoningDRuns well2.0 tok/s114400 ms2.2M
RAGDRuns well2.0 tok/s176000 ms4.3M

Quantization options

How Falcon H1 Tiny 90M Instruct (0.09000000357627869B params) fits at each quantization level on RX 6800 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
0.0 GB
LowC45
Q3_K_S
3
0.0 GB
LowC45
NVFP4
4
0.1 GB
MediumC45
Q4_K_M
4
0.1 GB
MediumC45
Q5_K_M
5
0.1 GB
HighC45
Q6_K
6
0.1 GB
HighC45
Q8_0
8
0.1 GB
Very HighC45
F16Best for your GPU
16
0.2 GB
MaximumC45

Get started

Copy-paste commands to run Falcon H1 Tiny 90M Instruct on your machine.

Run

lms load hf-tiiuae--falcon-h1-tiny-90m-instruct-gguf && lms server start

Opciones de mejora

Hardware que ejecuta bien Falcon H1 Tiny 90M Instruct

MacBook Pro M4 32GBOpción económica
32 GB Unified (+16)
D
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.2 tok/s decodificación

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$799 MSRP

MacBook Pro M3 24GBMejor relación calidad-precio
24 GB Unified (+8)
D
El modelo cabe en memoria compartida, pero ahora el verdadero límite es el ancho de banda de esa memoria.2 tok/s decodificación

~$1,099 MSRP

Frequently asked questions

Can RX 6800 16GB run Falcon H1 Tiny 90M Instruct?

Yes, RX 6800 16GB can run Falcon H1 Tiny 90M Instruct with a D grade (Runs well). Expected decode speed: 2.0 tok/s.

How much VRAM does Falcon H1 Tiny 90M Instruct need?

Falcon H1 Tiny 90M Instruct (0.09000000357627869B parameters) requires approximately 2.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Falcon H1 Tiny 90M Instruct?

The recommended quantization for Falcon H1 Tiny 90M Instruct is Q4_K_M, which balances quality and memory efficiency.

What speed will Falcon H1 Tiny 90M Instruct run at on RX 6800 16GB?

On RX 6800 16GB, Falcon H1 Tiny 90M Instruct achieves approximately 2.0 tokens per second decode speed with a time-to-first-token of 96800ms using Q4_K_M quantization.

Can RX 6800 16GB run Falcon H1 Tiny 90M Instruct for coding?

For coding workloads, Falcon H1 Tiny 90M Instruct on RX 6800 16GB receives a D grade with 2.0 tok/s and 2.2M context.

What context window can Falcon H1 Tiny 90M Instruct use on RX 6800 16GB?

On RX 6800 16GB, Falcon H1 Tiny 90M Instruct can safely use up to 2.2M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Falcon H1 Tiny 90M Instruct feels slow on RX 6800 16GB?

Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

See all results for RX 6800 16GBSee all hardware for Falcon H1 Tiny 90M Instruct
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-tiiuae--falcon-h1-tiny-90m-instruct-gguf-on-rx-6800-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: