mlx-community / text-generation updated 4 months ago

gpt-oss-20b-MXFP4-Q8

Name: gpt-oss-20b-MXFP4-Q8
Author: mlx-community

This model mlx-community/gpt-oss-20b-MXFP4-Q8 was converted to MLX format from openai/gpt-oss-20b using mlx-lm version 0.27.0.

Params

20.9 B

Context

131,072

Downloads 30d

355 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

355 K346 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u32	12.1 GB	16.9 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	12.1 GB	64.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/gpt-oss-20b-mxfp4-q8
{
  "hf_id": "mlx-community/gpt-oss-20b-MXFP4-Q8",
  "params_b": 20.91,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 355273,
  "vram_estimates": [
    { "quant": "u32", "gb": 16.9 }
  ],
  "updated_at": "2026-07-28T18:06:09Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: GptOssForCausalLM
Parameters: 20.9 B
Tensor type: U32
Context length: 131,072
Vocabulary: 201,088
Layers / heads: 24 / 64
Licence: apache-2.0
First seen on the Hub: 2025-08-29
Base model: gpt-oss-20b
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base gpt-oss-20b openai 8.6 M

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M Llama-3.1-8B-Instruct 8.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB