RTX 5070 12GBコスパ重視12 GB VRAM (+1)672 GB/s (+56)
B
This setup is broadly balanced for this model.93.3 tok/sデコード
〜$549 MSRP
Can Aya Expanse 8B run on RTX 2080 Ti 11GB?
YES — Runs Great
B58Good
Estimated from fit model
Aya Expanse 8B needs ~8.8 GB VRAM. RTX 2080 Ti 11GB has 11.0 GB. With Q4_K_M quantization, expect ~88 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: StandardBottleneck: Balanced
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) — 8.8 GB, 88.2 tok/s, Runs well
8.8 GB required11.0 GB available
80% VRAM used
Fit status
Runs well
Decode
88.2 tok/s
TTFT
2195 ms
Safe context
8K
Memory
8.8 GB / 11.0 GB
Memory breakdown
Weights4.9 GB
KV Cache2.0 GB
Runtime0.9 GB
Headroom1.1 GB
See how fast it feels
See how fast it feelsAya Expanse 8B on RTX 2080 Ti 11GB
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: 88.2 tok/s decode · 2.2s TTFT (warm) · 221 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 88.2 tok/s | 1197 ms | 8K |
| Coding | B | Runs well | 88.2 tok/s | 2195 ms | 8K |
| Agentic Coding | B | Runs with offload | 88.2 tok/s | 3193 ms | 8K |
| Reasoning | B | Runs well | 88.2 tok/s | 2594 ms | 8K |
| RAG | B | Runs with offload | 88.2 tok/s | 3991 ms | 8K |
Inference speed
Aya Expanse 8B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Aya Expanse 8B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~152 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
| RTX 5090 32GB | 32 GB | Q4_K_M | 152.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 128.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 112.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 107.7 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 102.2 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 96.9 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 96.0 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 82.6 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 82.6 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 76.6 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 52.9 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 48.5 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 44.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 42.6 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 26.3 | Offloads |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quantization options
How Aya Expanse 8B (8B params) fits at each quantization level on RTX 2080 Ti 11GB (11.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | C52 |
Q3_K_S | 3 | 3.9 GB | Low | C53 |
NVFP4 | 4 | 4.5 GB | Medium | C54 |
Q4_K_M | 4 | 4.9 GB | Medium | C54 |
Q5_K_M | 5 | 5.8 GB | High | C54 |
Q6_KBest for your GPU | 6 | 6.6 GB | High | C54 |
Q8_0 | 8 | 8.6 GB | Very High | F0 |
F16 | 16 | 16.4 GB | Maximum | F0 |
Get started
Copy-paste commands to run Aya Expanse 8B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "CohereForAI/aya-expanse-8b" \
--hf-file "aya-expanse-8b-Q4_K_M.gguf" \
-c 4096 -ngl 99アップグレードオプション
Aya Expanse 8Bを快適に動かすハードウェア
Frequently asked questions
Can RTX 2080 Ti 11GB run Aya Expanse 8B?
Yes, RTX 2080 Ti 11GB can run Aya Expanse 8B with a B grade (Runs well). Expected decode speed: 88.2 tok/s.
How much VRAM does Aya Expanse 8B need?
Aya Expanse 8B (8B parameters) requires approximately 8.8 GB of memory with Q4_K_M quantization.
What is the best quantization for Aya Expanse 8B?
The recommended quantization for Aya Expanse 8B is Q4_K_M, which balances quality and memory efficiency.
What speed will Aya Expanse 8B run at on RTX 2080 Ti 11GB?
On RTX 2080 Ti 11GB, Aya Expanse 8B achieves approximately 88.2 tokens per second decode speed with a time-to-first-token of 2195ms using Q4_K_M quantization.
Can RTX 2080 Ti 11GB run Aya Expanse 8B for coding?
For coding workloads, Aya Expanse 8B on RTX 2080 Ti 11GB receives a B grade with 88.2 tok/s and 8K context.
What context window can Aya Expanse 8B use on RTX 2080 Ti 11GB?
On RTX 2080 Ti 11GB, Aya Expanse 8B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/aya-expanse-8b-on-rtx-2080-ti-11gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: