GPT-OSS 20B needs ~19.6 GB VRAM. MacBook Pro M2 Pro 32GB has 23.0 GB. With Q4_K_M quantization, expect ~27 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
Tight fit
Decode
26.9 tok/s
TTFT
7203 ms
Safe context
38K
Memory
19.6 GB / 23.0 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs well | 26.9 tok/s | 3929 ms | 38K |
| Coding | S | Tight fit | 26.9 tok/s | 7203 ms | 38K |
| Agentic Coding | S | Runs with offload | 26.9 tok/s | 10478 ms | 38K |
| Reasoning | S | Tight fit | 26.9 tok/s | 8513 ms | 38K |
| RAG | S | Runs with offload | 26.9 tok/s | 13097 ms | 38K |
Inference speed
Estimated decode speed (tokens/sec) for GPT-OSS 20B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~231 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 | 230.5 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 147.1 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 132.7 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 125.8 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 106.9 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 89.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 84.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 68.2 | Heavy offload |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 66.0 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 66.0 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 46.1 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 42.2 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 40.4 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 24.2 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 15.2 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 5.7 | 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 GPT-OSS 20B (21B params) fits at each quantization level on MacBook Pro M2 Pro 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.2 GB | Low | S87 |
Q3_K_S | 3 | 10.3 GB | Low | S88 |
NVFP4 | 4 | 11.8 GB | Medium | S89 |
Q4_K_M | 4 | 12.8 GB | Medium | S89 |
Q5_K_M | 5 | 15.1 GB | High | S88 |
Q6_KBest for your GPU | 6 | 17.2 GB | High | S88 |
Q8_0 | 8 | 22.5 GB | Very High | F0 |
F16 | 16 | 43.1 GB | Maximum | F0 |
Copy-paste commands to run GPT-OSS 20B on your machine.
Run
ollama run gpt-ossYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | A | 19 tok/s | |
| Qwen 3.5 27B | 27B | S | 8.5 tok/s | |
| Qwen 3.6 27B | 27B | S | 7 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 20.1 tok/s | |
| Qwen 3.5 35B A3B | 35B | A | 16.6 tok/s |
Yes, MacBook Pro M2 Pro 32GB can run GPT-OSS 20B with a S grade (Tight fit). Expected decode speed: 26.9 tok/s.
GPT-OSS 20B (21B parameters) requires approximately 19.6 GB of memory with Q4_K_M quantization.
The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M2 Pro 32GB, GPT-OSS 20B achieves approximately 26.9 tokens per second decode speed with a time-to-first-token of 7203ms using Q4_K_M quantization.
For coding workloads, GPT-OSS 20B on MacBook Pro M2 Pro 32GB receives a S grade with 26.9 tok/s and 38K context.
On MacBook Pro M2 Pro 32GB, GPT-OSS 20B can safely use up to 38K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Not always. MacBook Pro M2 Pro 32GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/gpt-oss-20b-on-m2-pro-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: