Instructions to use ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX")
config = load_config("ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX 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 "ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX"

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 ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Geer Sage-A1.5 35B-A3B (4/8-bit MLX)

This is Geer's independent 4/8-bit MLX conversion of Sage-A1.5 from Shanghai AI Laboratory. It retains the model's native vision tower and processor assets.

Build and changes

Source: InternScience/Sage-A1.5
Immutable source revision: 0e3205cf441cf01df0c0d238cc4738d0e43b4ca7
BF16 source payload: 71,931,809,355 bytes, including the source MTP file
Architecture: qwen3_5_moe
Conversion: qwen3_5_moe_unfused_experts in Geer's build tool
Conversion packages: MLX 0.32.0, MLX-LM 0.31.3, MLX-VLM 0.6.3, huggingface-hub 1.24.0, hf-xet 1.5.2, safetensors 0.8.0
Converted size and file hashes: recorded by geer-build-manifest.json

Affine mixed 4/8-bit, group size 64. Routed expert gate, up, and down projections use 4 bits. Other eligible language-model matrices use 8 bits, including embeddings, attention and Gated DeltaNet projections, routers, shared experts, and the language-model head. The vision tower, norms, and other non-quantized parameters remain BF16. The transformation fuses the source's individually stored routed experts for MLX-VLM. Its pinned sanitizer omits the source mtp.* tensors. This artifact therefore does not supply native MTP or claim speculative-decoding support.

Geer changes the weight layout and precision, rewrites conversion metadata, and supplies this card, licenses, and attribution notices. MLX-VLM may also normalize tokenizer and processor metadata. NOTICE identifies these changes. The source and build manifests record the exact original and output files, including the tokenizer, chat template, configurations, and tensors.

The artifact includes the pinned geer-recipe.toml, complete geer-source-manifest.json, and geer-build-manifest.json. The completed conversion passed full file-size and SHA-256 verification. Reproduce it with Geer's download, convert, and verify commands using the included recipe.

Evaluation and use

Upstream benchmark reports describe the source model. They are reported quality proxies, not measured results for this quantization. Geer does not claim that conversion preserves any benchmark score.

Image inputs are native to the model. Full serving and computer-use task qualification remains incomplete. Retaining vision tensors alone does not verify image serving or application compatibility. Compatibility checks use Geer-pinned oMLX 0.5.3, revision 31d07a7fdbbb499d4520188fb7e8f7bdbfe4c770; results apply only to the tested artifact and application path.

The source configuration's 262,144-token context limit is not a qualified useful-context or latency result. This artifact does not establish support for a 16 GB Mac or another untested chip and memory configuration.

License and provenance

The pinned source card declares apache-2.0 and describes Qwen3.6-35B-A3B and Agents-A1 as its bases. The pinned Sage snapshot has no separate LICENSE or NOTICE file. LICENSE supplies the standard Apache License 2.0 text. LICENSE-QWEN preserves the Qwen license and attribution. NOTICE records the declared lineage, evidence, and Geer's modifications. Geer's MIT project license does not replace the model's Apache license.

The evidence below identifies source files independently of local paths. The full source manifest supplies the remaining hashes.

Source file	SHA-256
README.md	`6018232fad99dd25660741525f2a76d8258dfef6620e930a33e4bbf4a9d0c914`
config.json	`93a4693fa9d8392fbfccd4b3c9873f4bfdcb14fdede978b123d07d19675efe99`
model.safetensors.index.json	`c49171ab39575c4b9b1accc2d8525aaba82626f2f1374bd0ed5ae86458d1c6ba`
chat_template.jinja	`0080393e13df7322bed792a78e75daf8a0374a80928996e5cf3cfd2ab4c1e1be`
tokenizer.json	`87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4`
tokenizer_config.json	`d403d02cf04f618863360c5f6d9043683d54544bab6da2d2e365fbcb089f30ce`

The source describes training lineage; it does not identify immutable parent weight revisions. The pinned parent evidence in NOTICE documents the license review, not a claim that those parent snapshots reproduce Sage's training. Geer does not assert rights to upstream trademarks or endorsement by Shanghai AI Laboratory, the Agents-A1 contributors, or Alibaba Cloud.

Downloads last month: 112

Safetensors

Model size

35B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for ilyakam/Geer-Sage-A1.5-35B-A3B-4-8bit-MLX

Base model

InternScience/Sage-A1.5

Quantized

(41)

this model