Instructions to use mlx-community/Tmax-9B-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Tmax-9B-MLX-bf16 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Tmax-9B-MLX-bf16")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/Tmax-9B-MLX-bf16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Tmax-9B-MLX-bf16"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/Tmax-9B-MLX-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Tmax-9B-MLX-bf16 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Tmax-9B-MLX-bf16"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mlx-community/Tmax-9B-MLX-bf16

Run Hermes

hermes

MLX LM

How to use mlx-community/Tmax-9B-MLX-bf16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Tmax-9B-MLX-bf16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Tmax-9B-MLX-bf16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Tmax-9B-MLX-bf16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Tmax-9B MLX (bf16)

MLX-converted text-only weights of allenai/tmax-9b.

The upstream base ships as a multimodal Qwen3_5ForConditionalGeneration config but contains zero vision tensors in its safetensors — i.e. it is already a text-only checkpoint with stub vision metadata. This release strips the residual vision_config / image-token entries so it loads cleanly via mlx_lm without a vision tower.

Source: allenai/tmax-9b
License: Apache-2.0
Variant: bf16
Quantized by: raullenchai
Tooling: mlx-lm 0.31.3 (the upstream mlx_vlm 0.3.12 qwen3_5 loader hard-requires vision-tower weights that this base does not ship, so the text-only mlx_lm.convert path is used instead)
Chat template: ships with the source repo (chat_template.jinja)
Tool format: qwen3_xml-compatible (<tool_call>{json}</tool_call>)

Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Tmax-9B-MLX-bf16")
print(generate(model, tokenizer, prompt="Hello", max_tokens=32))

Notes

This is a pure text-generation MLX release. No vision/image inputs.
For best chat behavior, use the chat template that ships with this repo.

Benchmarks

Measured on M3 Ultra Studio (28 (20 Performance and 8 Efficiency) CPU, 60-core GPU, 256 GB unified memory) via rapid-mlx 0.8.18. Medians of 3 runs.

Variant	Decode tok/s	TTFT (ms)	Prefill 1k (tok/s)	Prefill 4k (tok/s)	Prefill 16k (tok/s)	Tool-call e2e
Tmax-9B (bf16 MLX)	—	—	—	—	—	—

⚠️ Note: weights load successfully, but the first streaming TTFT call never returned in our bench harness (43 min, watchdog killed). This is bf16-specific — the 4 / 6 / 8 bit Tmax-9B variants stream cleanly. Recommend the quantized variants for streaming workloads until root-caused.

Full results (all 7 Tmax MLX variants + 2 Qwen3.5 controls): rapid-mlx docs.

Reproduce:

pip install rapid-mlx==0.8.18
rapid-mlx serve tmax-9b-bf16 --port 8765

Downloads last month: 46

Safetensors

Model size

9B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for mlx-community/Tmax-9B-MLX-bf16

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

allenai/tmax-9b

Finetuned

(1)

this model