AMD Instinct MI350X 288GBOpción económica
288 GB VRAM (+32)8000 GB/s (+2000)
C
Sube la velocidad estimada de decodificación alrededor de un 33%.90.9 tok/s decodificación
Sube la velocidad estimada de decodificación alrededor de un 33%.
~$8,000 MSRP
Can Qwen3.5 122B A10B run on AMD Instinct MI325X 256GB?
YES — Runs Great
C50Usable
Estimated from fit model
Qwen3.5 122B A10B needs ~100.6 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q3_K_M quantization, expect ~68 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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
F16 (Maximum quality) — 290.9 GB, 14.1 tok/s, Very compromised (needs ~30 GB host RAM)
290.9 GB required256.0 GB available
114% VRAM needed
34.9 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~30 GB host RAM)
Decode
14.1 tok/s
TTFT
13778 ms
Safe context
4K
Memory
290.9 GB / 256.0 GB
Offload
10%
Memory breakdown
Weights250.1 GB
KV Cache14.3 GB
Runtime0.9 GB
Headroom25.6 GB
See how fast it feels
See how fast it feelsQwen3.5 122B A10B on AMD Instinct MI325X 256GB
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: 14.1 tok/s decode · 13.8s TTFT (warm) · 35 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 68.1 tok/s | 1550 ms | 190K |
| Coding | C | Runs well | 68.1 tok/s | 2841 ms | 190K |
| Agentic Coding | C | Runs well | 68.1 tok/s | 4133 ms | 190K |
| Reasoning | C | Runs well | 68.1 tok/s | 3358 ms | 190K |
| RAG | C | Runs well | 68.1 tok/s | 5166 ms | 190K |
Quantization options
How Qwen3.5 122B A10B (122B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 47.6 GB | Low | D40 |
Q3_K_S | 3 | 59.8 GB | Low | C41 |
NVFP4 | 4 | 68.3 GB | Medium | C42 |
Q4_K_M | 4 | 74.4 GB | Medium | C42 |
Q5_K_M | 5 | 87.8 GB | High | C43 |
Q6_K | 6 | 100.0 GB | High | C44 |
Q8_0Best for your GPU | 8 | 130.5 GB | Very High | C47 |
F16 | 16 | 250.1 GB | Maximum | F0 |
Get started
Copy-paste commands to run Qwen3.5 122B A10B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "unsloth/Qwen3.5-122B-A10B-GGUF" \
--hf-file "Qwen3.5-122B-A10B-GGUF-Q3_K_M.gguf" \
-c 4096 -ngl 99Opciones de mejora
Hardware que ejecuta bien Qwen3.5 122B A10B
Frequently asked questions
Can AMD Instinct MI325X 256GB run Qwen3.5 122B A10B?
Yes, AMD Instinct MI325X 256GB can run Qwen3.5 122B A10B with a C grade (Runs well). Expected decode speed: 68.1 tok/s.
How much VRAM does Qwen3.5 122B A10B need?
Qwen3.5 122B A10B (122B parameters) requires approximately 100.6 GB of memory with Q3_K_M quantization.
What is the best quantization for Qwen3.5 122B A10B?
The recommended quantization for Qwen3.5 122B A10B is Q3_K_M, which balances quality and memory efficiency.
What speed will Qwen3.5 122B A10B run at on AMD Instinct MI325X 256GB?
On AMD Instinct MI325X 256GB, Qwen3.5 122B A10B achieves approximately 68.1 tokens per second decode speed with a time-to-first-token of 2841ms using Q3_K_M quantization.
Can AMD Instinct MI325X 256GB run Qwen3.5 122B A10B for coding?
For coding workloads, Qwen3.5 122B A10B on AMD Instinct MI325X 256GB receives a C grade with 68.1 tok/s and 190K context.
What context window can Qwen3.5 122B A10B use on AMD Instinct MI325X 256GB?
On AMD Instinct MI325X 256GB, Qwen3.5 122B A10B can safely use up to 190K tokens of context. The model's official context limit is —, 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/hf-unsloth--qwen3-5-122b-a10b-gguf-on-instinct-mi325x-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: