Chat model

gpt-oss-20b on Apple silicon Macs

Released

Strong chat, writing and coding. Smarty Pants serves a pinned, quantized 4-bit MLX build on qualified Macs with 24 GB of memory or more, through an OpenAI-compatible API.

$0.027

$0.027 per million input tokens, $0.135 per million output tokens

Listed price on November 19, 2026. Current price: GET /v1/models.

gpt-oss-20b at a glance

What Smarty Pants serves, from its public catalog, and what the model's developer publishes about it.

API name
smartypants/gpt-oss-20b
Endpoint
POST /v1/chat/completions
Build served
4-bit MLX (gpt-oss-20b-mlx-optiq-4bit-r01ca7c6)
Mac memory needed
24 GB or more
Context on Smarty Pants
16,384 tokens
Max output
4,096 tokens
Developer
OpenAI
Parameters
21B, 3.6B active per token
License
Apache-2.0
Upstream context
131,072 tokens
First released
August 2025
Status
Released

Smarty Pants catalog checked November 19, 2026. Upstream facts from the developer's model card (sources below).

What gpt-oss-20b is good for

Smaller of OpenAI's two open-weight gpt-oss models, meant for lower-latency, local or specialised use: reasoning, agentic tasks, function calling, web browsing, Python code execution and structured outputs.

Reasoning effort is adjustable (low, medium, high), and the MoE weights were post-trained in MXFP4 so the model runs within 16 GB of memory; it must be used with OpenAI's harmony response format.

Use it for

  • Reasoning and tool use at a low listed price
  • Structured output

Look elsewhere for

  • Inputs longer than 16,384 tokens

How to call gpt-oss-20b

Smarty Pants works with OpenAI's libraries: change the base URL and the key, and keep the rest. Get a key at smartypants.network/api.

from openai import OpenAI

client = OpenAI(base_url="https://smartypants.network/v1", api_key="YOUR_SMARTY_PANTS_KEY")

reply = client.chat.completions.create(
    model="smartypants/gpt-oss-20b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)

Before sending real traffic, check is_ready for this model on GET /v1/models. A 429 or 503 means no Mac can take the request right now: wait the Retry-After seconds or use your fallback provider.

Which Macs can serve gpt-oss-20b

Smarty Pants serves this model only on Macs with 24 GB of unified memory or more. These Apple silicon chips were sold with at least one memory size that big (memory options from Apple's tech specs).

ChipMemory sizes that fitMemory sizes too small
M1 Pro 32 GB 16 GB
M1 Max 32 GB, 64 GB None
M1 Ultra 64 GB, 128 GB None
M2 24 GB 8 GB, 16 GB
M2 Pro 32 GB 16 GB
M2 Max 32 GB, 64 GB, 96 GB None
M2 Ultra 64 GB, 128 GB, 192 GB None
M3 24 GB 8 GB, 16 GB
M3 Pro 36 GB 18 GB
M3 Max 36 GB, 48 GB, 64 GB, 96 GB, 128 GB None
M3 Ultra 96 GB, 256 GB, 512 GB None
M4 24 GB, 32 GB 16 GB
M4 Pro 24 GB, 48 GB, 64 GB None
M4 Max 36 GB, 48 GB, 64 GB, 128 GB None
M5 24 GB, 32 GB 16 GB
M5 Pro 24 GB, 48 GB, 64 GB None
M5 Max 36 GB, 48 GB, 64 GB, 128 GB None
M5 Ultra 96 GB, 256 GB, 512 GB None
M6 24 GB, 32 GB 16 GB

No memory option is big enough on: M1.

Frequently asked questions

What is the API name for gpt-oss-20b on Smarty Pants?

Use "smartypants/gpt-oss-20b" as the model with the OpenAI-compatible base URL https://smartypants.network/v1.

How much does gpt-oss-20b cost on Smarty Pants?

The listed price on November 19, 2026 was $0.027 per million input tokens, $0.135 per million output tokens. Prices can change; GET https://smartypants.network/v1/models returns the current price, and you are not charged for a request Smarty Pants can't serve.

How much memory does a Mac need to serve gpt-oss-20b?

Smarty Pants serves this 4-bit MLX build only on qualified Apple silicon Macs with 24 GB of unified memory or more.

What context length does gpt-oss-20b have on Smarty Pants?

Smarty Pants accepts up to 16,384 tokens per request and writes up to 4,096. The upstream model card lists 131,072 tokens; Smarty Pants serves a smaller window so the model fits on Macs.

Is gpt-oss-20b available right now?

On November 19, 2026 it was released. How many Macs have it online changes through the day; check is_ready on https://smartypants.network/v1/models before sending real traffic, and keep a fallback provider.

Can I send private data to gpt-oss-20b on Smarty Pants?

Requests on the general network run on Macs other people own, and a serving Mac decrypts a request in memory to answer it. Keep secrets, personal and confidential data off the general network; companies can run work on their own Macs with a Group.

Sources

  1. Smarty Pants: GET /v1/models (checked November 19, 2026)
  2. Smarty Pants: API page
  3. Hugging Face: openai/gpt-oss-20b model card
  4. Hugging Face: openai/gpt-oss-20b config.json
  5. Hugging Face API: openai/gpt-oss-20b (createdAt)

Other chat models

Try a pinned open model on real Macs.

See every model, its listed price and the code to call it. Smarty Pants works with the OpenAI SDK you already use: change the base URL and the key.

Requests run on Macs owned by other people. Owners agree not to read requests and the app doesn't show them, but a serving Mac decrypts each request in memory to answer it, so that is a rule and a design, not a technical guarantee. Don't send sensitive data on the general network.