Qwen3.5 122B A10B needs ~94.2 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q3_K_M quantization, expect ~64 tok/s.
Operating mode
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
92.5 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
7.6 tok/s
TTFT
25524 ms
Safe context
4K
Memory
284.5 GB / 192.0 GB
Offload
30%
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 64.3 tok/s | 1642 ms | 125K |
| Coding | C | Runs well | 64.3 tok/s | 3010 ms | 125K |
| Agentic Coding | C | Runs well | 64.3 tok/s | 4379 ms | 125K |
| Reasoning | C | Runs well | 64.3 tok/s | 3558 ms | 125K |
| RAG | C | Runs well | 64.3 tok/s | 5473 ms | 125K |
Inference speed
Estimated decode speed (tokens/sec) for Qwen3.5 122B A10B at Q3_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~9 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? |
|---|---|---|---|---|
MacBook Pro M4 Max 128GB | 128 GB | Q3_K_M | 9.3 | Offloads |
Mac Studio M3 Ultra 256GB | 256 GB | Q3_K_M | 8.7 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q3_K_M | 7.2 | Offloads |
Mac Studio M1 Ultra 128GB | 128 GB | Q3_K_M | 6.8 | Offloads |
2× RX 7900 XTX 24GB | 48 GB | Q3_K_M | 4.7 | Too big |
MacBook Pro M4 Max 64GB | 64 GB | Q3_K_M | 4.5 | Too big |
 RTX 5090 32GB | 32 GB | Q3_K_M | 2.8 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q3_K_M | 2.6 | Too big |
| 2× RTX 4090 24GB | 48 GB | Q3_K_M | 2.5 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q3_K_M | 2.3 | Too big |
| RTX 4090 24GB | 24 GB | Q3_K_M | 2.0 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q3_K_M | 2.0 | Too big |
| RTX 3090 24GB | 24 GB | Q3_K_M | 2.0 | Too big |
| RTX 4070 12GB | 12 GB | Q3_K_M | 2.0 | Too big |
| RTX 3060 12GB | 12 GB | Q3_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q3_K_M | 2.0 | Too big |
RX 7900 XTX 24GB | 24 GB | Q3_K_M | 2.0 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q3_K_M | 2.0 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q3_K_M | 2.0 | Too big |
| 4× RTX 3060 12GB | 48 GB | Q3_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q3_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.
How Qwen3.5 122B A10B (122B params) fits at each quantization level on AMD Instinct MI300X 192GB (192.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 47.6 GB | Low | C42 |
Q3_K_S | 3 | 59.8 GB | Low | C43 |
NVFP4 | 4 | 68.3 GB | Medium | C44 |
Q4_K_M | 4 | 74.4 GB | Medium | C45 |
Q5_K_M | 5 | 87.8 GB | High | C46 |
Q6_K | 6 | 100.0 GB | High | C47 |
Q8_0Best for your GPU | 8 | 130.5 GB | Very High | C48 |
F16 | 16 | 250.1 GB | Maximum | F0 |
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 99Yes, AMD Instinct MI300X 192GB can run Qwen3.5 122B A10B with a C grade (Runs well). Expected decode speed: 64.3 tok/s.
Qwen3.5 122B A10B (122B parameters) requires approximately 94.2 GB of memory with Q3_K_M quantization.
The recommended quantization for Qwen3.5 122B A10B is Q3_K_M, which balances quality and memory efficiency.
On AMD Instinct MI300X 192GB, Qwen3.5 122B A10B achieves approximately 64.3 tokens per second decode speed with a time-to-first-token of 3010ms using Q3_K_M quantization.
For coding workloads, Qwen3.5 122B A10B on AMD Instinct MI300X 192GB receives a C grade with 64.3 tok/s and 125K context.
On AMD Instinct MI300X 192GB, Qwen3.5 122B A10B can safely use up to 125K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
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-mi300x-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: