Qwen AgentWorld 35B A3B needs ~24.8 GB VRAM. RTX PRO 4000 Blackwell 24GB has 24.0 GB. With Q4_K_M quantization, expect ~56 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
0.8 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.7 GB host RAM)
Decode
56.3 tok/s
TTFT
3438 ms
Safe context
4K
Memory
24.8 GB / 24.0 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs with offload (needs ~0.5 GB host RAM) | 57.0 tok/s | 1852 ms | 4K |
| Coding | A | Runs with offload (needs ~0.7 GB host RAM) | 56.3 tok/s | 3438 ms | 4K |
| Agentic Coding | A | Runs with offload (needs ~0.9 GB host RAM) | 54.9 tok/s | 5127 ms | 4K |
| Reasoning | A | Runs with offload (needs ~0.7 GB host RAM) | 56.3 tok/s | 4063 ms | 4K |
| RAG | A | Runs with offload (needs ~0.9 GB host RAM) | 54.9 tok/s | 6408 ms | 4K |
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? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 140.4 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 80.0 | Offloads |
Mac Studio M3 Ultra 256GB | 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 |
| RTX 3090 24GB | 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 |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 29.1 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 10.2 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 6.0 | Too big |
| RTX 4060 8GB | 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.
How Qwen AgentWorld 35B A3B (34.70000076293945B params) fits at each quantization level on RTX PRO 4000 Blackwell 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q1_0_G128 | 1.125 | 5.0 GB | Very Low | A79 |
Q2_0_G128 | 1.71 | 9.3 GB | Low | A81 |
Q2_K | 2 | 13.5 GB | Low | A82 |
Q3_K_SBest for your GPU | 3 | 17.0 GB | Low | A82 |
NVFP4 | 4 | 19.4 GB | Medium | F0 |
Q4_K_M | 4 | 21.2 GB | Medium | F0 |
Q5_K_M | 5 | 25.0 GB | High | F0 |
Q6_K | 6 | 28.5 GB | High | F0 |
Q8_0 | 8 | 37.1 GB | Very High | F0 |
F16 | 16 | 71.1 GB | Maximum | F0 |
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 |
|---|---|---|---|---|
 Qwen 3.6 35B A3B | 35B | A | 37.9 tok/s | |
| Qwen 3.5 35B A3B | 35B | A | 50.2 tok/s | |
| Agents-A1 35B A3B | 35.1B | S | 54.7 tok/s |
Yes, RTX PRO 4000 Blackwell 24GB can run Qwen AgentWorld 35B A3B with a A grade (Runs with offload (needs ~0.7 GB host RAM)). Expected decode speed: 56.3 tok/s.
Qwen AgentWorld 35B A3B (34.70000076293945B parameters) requires approximately 24.8 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 RTX PRO 4000 Blackwell 24GB, Qwen AgentWorld 35B A3B achieves approximately 56.3 tokens per second decode speed with a time-to-first-token of 3438ms using Q4_K_M quantization.
For coding workloads, Qwen AgentWorld 35B A3B on RTX PRO 4000 Blackwell 24GB receives a A grade with 56.3 tok/s and 4K context.
On RTX PRO 4000 Blackwell 24GB, Qwen AgentWorld 35B A3B can safely use up to 4K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-agentworld-35b-a3b-on-rtx-pro-4000-blackwell-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: