Qwen AgentWorld 35B A3B needs ~36.1 GB VRAM. Intel Data Center GPU Max 1550 128GB has 128.0 GB. With Q4_K_M quantization, expect ~258 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
Fit status
Runs well
Decode
280.6 tok/s
TTFT
690 ms
Safe context
262K
Memory
35.2 GB / 128.0 GB
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 258.0 tok/s | 409 ms | 262K |
| Coding | A | Runs well | 258.0 tok/s | 750 ms | 262K |
| Agentic Coding | A | Runs well | 258.0 tok/s | 1091 ms | 262K |
| Reasoning | A | Runs well | 258.0 tok/s | 887 ms | 262K |
| RAG | A | Runs well | 258.0 tok/s | 1364 ms | 262K |
Inference speed
Estimated decode speed (tokens/sec) for Qwen AgentWorld 35B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~140 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? |
|---|---|---|---|---|
| 32 GB | Q4_K_M | 140.4 | Fits | |
| 24 GB | Q4_K_M | 80.0 | Offloads | |
How Qwen AgentWorld 35B A3B (34.70000076293945B params) fits at each quantization level on Intel Data Center GPU Max 1550 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q1_0_G128 | 1.125 | 5.0 GB | Very Low | A71 |
Q2_0_G128 | 1.71 | 9.3 GB | Low | A71 |
Q2_K | 2 |
Copy-paste commands to run Qwen AgentWorld 35B A3B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "Qwen/Qwen-AgentWorld-35B-A3B" \
--hf-file "Qwen-AgentWorld-35B-A3B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 29.2 tok/s | ||
| 122B | S |
Yes, Intel Data Center GPU Max 1550 128GB can run Qwen AgentWorld 35B A3B with a A grade (Runs well). Expected decode speed: 258.0 tok/s.
Qwen AgentWorld 35B A3B (34.70000076293945B parameters) requires approximately 36.1 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen AgentWorld 35B A3B is Q4_K_M, which balances quality and memory efficiency.
On Intel Data Center GPU Max 1550 128GB, Qwen AgentWorld 35B A3B achieves approximately 258.0 tokens per second decode speed with a time-to-first-token of 750ms using Q4_K_M quantization.
For coding workloads, Qwen AgentWorld 35B A3B on Intel Data Center GPU Max 1550 128GB receives a A grade with 258.0 tok/s and 262K context.
On Intel Data Center GPU Max 1550 128GB, Qwen AgentWorld 35B A3B can safely use up to 262K tokens of context. The model's official context limit is 262K, 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/qwen-agentworld-35b-a3b-on-max-1550-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| 256 GB |
| Q4_K_M |
| 77.5 |
| Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 67.5 | Offloads |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 64.6 | Fits |
| 24 GB | Q4_K_M | 64.0 | Offloads |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 61.2 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 47.9 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 47.9 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 36.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 33.7 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 32.2 | Fits |
| 16 GB | Q4_K_M | 29.1 | Too big |
| 12 GB | Q4_K_M | 10.2 | Too big |
| 12 GB | Q4_K_M | 6.0 | Too big |
| 8 GB | Q4_K_M | 4.4 | Too big |
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.
13.5 GB |
| Low |
| A71 |
Q3_K_S | 3 | 17.0 GB | Low | A71 |
NVFP4 | 4 | 19.4 GB | Medium | A72 |
Q4_K_M | 4 | 21.2 GB | Medium | A72 |
Q5_K_M | 5 | 25.0 GB | High | A72 |
Q6_K | 6 | 28.5 GB | High | A73 |
Q8_0 | 8 | 37.1 GB | Very High | A74 |
F16Best for your GPU | 16 | 71.1 GB | Maximum | A80 |
| 81 tok/s |
| 35B | S | 256.2 tok/s |
| 111B | S | 32.5 tok/s |
| 72B | S | 49.9 tok/s |
Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.