GPT OSS 120B — Hardware Requirements & GPU Compatibility
Chat
GPT OSS 120B is a 120B-parameter open language model from tripolskypetr in the GPT-OSS family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 72.41 GB of VRAM — see which GPUs and Macs can run it below.
GPT OSS 120B runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio M2 Max (96 GB) · Q4_K_M · 72.7 GB · ~38 tok/s
Macs from 64 GB (~54 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run GPT OSS 120B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve tripolskypetr/gpt-oss-120b --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 6000 (96 GB) (23 GB headroom) · Q4_K_M
- Generation speed
- ~152 tok/s
- generation speed
- Cost per 1M output tokens
- $2.66
- per 1M output tokens
How Much VRAM Does GPT OSS 120B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 51.4 GB | 52.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Does not fit: needs 51.7 GB | |
| 52.9 GB | 53.7 GB | 3-bit small — 3-bit small quantization | Does not fit: needs 53.2 GB | |
| 58.9 GB | 59.7 GB | 3-bit medium — 3-bit medium quantization | Does not fit: needs 59.2 GB | |
| 60.4 GB | 61.2 GB | 4-bit · legacy — 4-bit legacy quantization | Does not fit: needs 60.7 GB | |
| 72.4 GB | 73.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 72.7 GB | |
| 85.9 GB | 86.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 86.2 GB | |
| 99.4 GB | 100.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 99.7 GB | |
| 120.4 GB | 121.2 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 120.7 GB |
Selected Q4_K_M
4-bit medium quantization72.7GBat 16K context
- Weights
- 72.0 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 48.7 GB more
Which Hardware Can Run GPT OSS 120B?
Q4_K_M · 72.4 GBGPT OSS 120B (Q4_K_M) requires 72.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 95+ GB is recommended. Using the full 131K context window can add up to 3.3 GB, bringing total usage to 75.7 GB. No consumer GPU has enough memory. 32 devices with unified memory can run GPT OSS 120B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M2 Max (96 GB).
64–80 GB
Q4_K_M · best fit Q4_0 (60.7 GB)
3 Mac classes · 1 device family
M2 Ultra*64 GB~66Simulate output on Mac Pro M2 Ultra (64 GB)M5 Max64 GB~57Simulate output on Mac Studio M5 Max (64 GB)Orin~28Simulate output on NVIDIA Jetson AGX Orin 64GB96 GB
fits · 23.3 GB free · up to 128K ctx
1 Mac class
M3 Max*96 GB~31Simulate output on MacBook Pro 14" M3 Max (96 GB)
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to GPT OSS 120B
GPT-OSS family · 14 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.5 122B A10BAlibaba | 109.4 | 75.5 GB | —needs > 24 GB | same size |
| NVIDIA Nemotron 3 Super 120B A12B BF16NVIDIA | 95.8 | 74.7 GB | —needs > 24 GB | same size |
| Ling 3.0 Flash VLInclusion AI | — | 76 GB | —needs > 24 GB | same size |
| Leanstral 1.5 119B A6BMistral AI | — | 84 GB | —needs > 24 GB | same size |
| Qwen1.5 110BAlibaba | — | 72.4 GB | —needs > 24 GB | same size |
| Laguna S 2.1poolside | — | 72.5 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- tripolskypetr
- Family
- GPT-OSS
- Parameters
- 120B
- Active parameters
- 8.9B per token
- Architecture
- GptOssForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 201,088
- Release Date
- 2025-08-19
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does GPT OSS 120B need?
GPT OSS 120B requires 72.4 GB of VRAM at Q4_K_M, or 240.4 GB at BF16. Full 131K context adds up to 3.3 GB (75.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 120B × 4.8 bits ÷ 8 = 72 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 3.7 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run GPT OSS 120B?
No — GPT OSS 120B requires at least 51.4 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for GPT OSS 120B?
For GPT OSS 120B, Q4_K_M (72.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (82.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 51.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run GPT OSS 120B on a Mac?
Yes, but only at lower quantizations. The smallest Mac that can run GPT OSS 120B is Mac Mini M4 Pro (64 GB) at Q2_K; 41 of the 156 Macs we list can run it at some quantization. For Q4_K_M (72.4 GB) you need a Mac with more unified memory.
Can I run GPT OSS 120B locally?
Yes — GPT OSS 120B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is GPT OSS 120B?
At Q4_K_M, GPT OSS 120B can reach ~120 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 5.4 GB active ÷ (8000 × 0.65) = 1.035 ms, plus 36 layers × 0.055 ms = 1.980 ms, so 1000 ÷ 3.015 ms = ~332 tok/s
Estimated speed at Q4_K_M (72.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of GPT OSS 120B?
At Q4_K_M, the download is about 72.00 GB. The full-precision BF16 version is 240.00 GB. The smallest option (Q2_K) is 51.00 GB.
Which GPUs can run GPT OSS 120B?
No single consumer GPU has enough VRAM to run GPT OSS 120B at Q4_K_M (72.4 GB). Multi-GPU or professional hardware is required.
Which devices can run GPT OSS 120B?
32 devices with unified memory can run GPT OSS 120B at Q4_K_M (72.4 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.