OpenModelsHQ

gpt-oss-120b

OpenAILLMMoEApache-2.0

gpt-oss-120b is an open-weight language model from OpenAI with 117B parameters (mixture of experts). At 4-bit it needs about 77.4 GB of memory, so the smallest current device that fits it is the RTX PRO 6000 Blackwell.

Overview

Estimated memory at 4-bit
77.4GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
117B
Mixture of experts, all weights counted
Context window
128K
131,072 tokens
Cheapest API, blended / 1M
$0.045
₹4.24 · PrimeIntellect · 3:1 input to output
All OpenAI API prices

Key information

Lab
OpenAI
Released
4 Aug 2025
Parameters
117B · MoE
Type
Language
Context
131,072 tokens
License
Apache-2.0
HF downloads, 30 days
2,433,479
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
gpt-oss-120b needs about 77.4 GB at 4-bit, 136.6 GB at 8-bit and 257.4 GB at 16-bit. At 4-bit it fits DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q477.4 GB
Q8136.6 GB
BF16257.4 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 77.4 GBToo big 215%RTX PRO 6000 Blackwell96 GB memory
8-bit (Q8)≈ 136.6 GBToo big 379%Mac Studio M5 Ultra (256GB)256 GB memory
16-bit (BF16)≈ 257.4 GBToo big 715%RubinAnnounced288 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

lmstudio-community/gpt-oss-120b-MLX-8bitCheck your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

ggml-org/gpt-oss-120b-GGUFFind compatible hardware

Through an API

PrimeIntellect (fp4) is the cheapest provider we found.

$0.035 / $0.075

Input / output per 1M tokens
₹3.30 / ₹7.07 at ₹94.29 per $1

Blended: $0.045 (₹4.24) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_lm.generate --model lmstudio-community/gpt-oss-120b-MLX-8bit \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf ggml-org/gpt-oss-120b-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

Hosted API 23

USD and INR per million tokensAll OpenAI API prices
Precision
PrimeIntellectCheapest$0.045₹4.24$0.035₹3.30$0.075₹7.07131,072FP4
Near AI$0.06₹5.66$0.03₹2.83$0.15₹14131,072FP4
Venice$0.06₹5.66$0.03₹2.83$0.15₹14128,000INT4
CoreWeave$0.065₹6.13$0.03₹2.83$0.17₹16131,072FP4
DekaLLM$0.0675₹6.36$0.03₹2.83$0.18₹17131,072BF16
AkashML$0.0693₹6.53$0.03₹2.83$0.187₹18131,072FP4
DeepInfra$0.0703₹6.62$0.037₹3.49$0.17₹16131,072BF16
Crusoe$0.10₹9.43$0.05₹4.71$0.25₹24131,072BF16
Mancer 2$0.1038₹9.78$0.055₹5.19$0.25₹24131,072FP8
Sail Research$0.145₹14$0.06₹5.66$0.40₹38131,072FP4
DigitalOcean$0.15₹14$0.06₹5.66$0.42₹40128,000Not listed
Google$0.1575₹15$0.09₹8.49$0.36₹34131,072Not listed
BaseTen$0.20₹19$0.10₹9.43$0.50₹47128,072FP4
Amazon Bedrock$0.2625₹25$0.15₹14$0.60₹57131,072Not listed
Groq$0.2625₹25$0.15₹14$0.60₹57131,072Not listed
Nebius$0.2625₹25$0.15₹14$0.60₹57131,072FP4
SiliconFlow$0.2625₹25$0.15₹14$0.60₹57131,072FP8
Together$0.2625₹25$0.15₹14$0.60₹57131,072Not listed
Parasail$0.2625₹25$0.10₹9.43$0.75₹71131,072FP4
Io Net$0.30₹28$0.25₹24$0.45₹42131,052FP4
SambaNova$0.3425₹32$0.14₹13$0.95₹90131,072Not listed
DeepInfra$0.3875₹37$0.20₹19$0.95₹90131,072FP8
Cerebras$0.45₹42$0.35₹33$0.75₹71131,072FP16
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does gpt-oss-120b need? At an 8k context, about 77.4 GB at 4-bit, 136.6 GB at 8-bit and 257.4 GB at 16-bit (BF16). A longer context needs more.

Can I run gpt-oss-120b on a Mac? The smallest current Mac that fits the 4-bit estimate of 77.4 GB is the Mac Studio M5 Max (128GB). An MLX build is available: lmstudio-community/gpt-oss-120b-MLX-8bit.

Does the full context fit? gpt-oss-120b supports up to 131,072 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is PrimeIntellect, at $0.04 per 1M input tokens and $0.08 per 1M output tokens (₹3.30 and ₹7.07 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources