MacBook Pro M4 32GBコスパ重視
32 GB Unified (+20)
D
Adds memory headroom for longer context windows and future model growth.2 tok/sデコード
Adds memory headroom for longer context windows and future model growth.
〜$799 MSRP
Can Falcon H1 Tiny 90M Instruct run on RX 7700 XT 12GB?
YES — Runs Great
D34Poor
Estimated from fit model
Falcon H1 Tiny 90M Instruct needs ~2.3 GB VRAM. RX 7700 XT 12GB has 12.0 GB. With Q4_K_M quantization, expect ~2 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Memory bandwidth
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.
Select quantization to explore
Q4_K_M (Medium quality) — 2.3 GB, 2.0 tok/s, Runs well
2.3 GB required12.0 GB available
19% VRAM used
Fit status
Runs well
Decode
2.0 tok/s
TTFT
96800 ms
Safe context
1.6M
Memory
2.3 GB / 12.0 GB
Memory breakdown
Weights0.1 GB
KV Cache0.1 GB
Runtime0.9 GB
Headroom1.2 GB
See how fast it feels
See how fast it feelsFalcon H1 Tiny 90M Instruct on RX 7700 XT 12GB
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
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | D | Runs well | 2.0 tok/s | 52800 ms | 788K |
| Coding | D | Runs well | 2.0 tok/s | 96800 ms | 1.6M |
| Agentic Coding | D | Runs well | 2.0 tok/s | 140800 ms | 3.2M |
| Reasoning | D | Runs well | 2.0 tok/s | 114400 ms | 1.6M |
| RAG | D | Runs well | 2.0 tok/s | 176000 ms | 3.2M |
Quantization options
How Falcon H1 Tiny 90M Instruct (0.09000000357627869B params) fits at each quantization level on RX 7700 XT 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.0 GB | Low | C46 |
Q3_K_S | 3 | 0.0 GB | Low | C46 |
NVFP4 | 4 | 0.1 GB | Medium | C46 |
Q4_K_M | 4 | 0.1 GB | Medium | C46 |
Q5_K_M | 5 | 0.1 GB | High | C46 |
Q6_K | 6 | 0.1 GB | High | C46 |
Q8_0 | 8 | 0.1 GB | Very High | C46 |
F16Best for your GPU | 16 | 0.2 GB | Maximum | C46 |
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アップグレードオプション
Falcon H1 Tiny 90M Instructを快適に動かすハードウェア
Frequently asked questions
Can RX 7700 XT 12GB run Falcon H1 Tiny 90M Instruct?
Yes, RX 7700 XT 12GB 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 2.3 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 7700 XT 12GB?
On RX 7700 XT 12GB, 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 7700 XT 12GB run Falcon H1 Tiny 90M Instruct for coding?
For coding workloads, Falcon H1 Tiny 90M Instruct on RX 7700 XT 12GB receives a D grade with 2.0 tok/s and 1.6M context.
What context window can Falcon H1 Tiny 90M Instruct use on RX 7700 XT 12GB?
On RX 7700 XT 12GB, Falcon H1 Tiny 90M Instruct can safely use up to 1.6M 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 7700 XT 12GB?
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.
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-7700-xt-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: