Instructions to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx 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("Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx")

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 Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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": "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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"

Ornith-1.0-35B-UD-Q5_K_XL-mlx / README.md

Brooooooklyn

Add model card

15aac65 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

7.15 kB

	---
	license: mit
	language:
	- en
	base_model: deepreinforce-ai/Ornith-1.0-35B
	tags:
	- mlx
	- mlx-node
	- quantized
	- qwen3.5
	- moe
	- hybrid-attention
	- gated-delta-net
	- vision-language
	- coding-agent
	- apple-silicon
	- 5-bit
	- unsloth-dynamic
	library_name: mlx-node
	quantized_by: mlx-node
	pipeline_tag: text-generation
	model_type: qwen3_5_moe
	---

	# Ornith-1.0-35B — UD-Q5_K_XL (mlx-node)

	5-bit base mixed-precision quantization of [deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) for Apple Silicon, using the Unsloth Dynamic per-tensor bit allocation (without imatrix AWQ) via [mlx-node](https://github.com/mlx-node/mlx-node).

	[Ornith-1.0](https://deep-reinforce.com/ornith.html) is a self-improving family of open-source agentic coding models. The 35B member is a Qwen3.5-VL-MoE (hybrid Gated-DeltaNet + full attention, 256 experts, vision-language) post-train.

	\| \| Original (BF16) \| This Model \|
	\|---\|---\|---\|
	\| Size \| ~68 GB \| 26 GB \|
	\| Format \| SafeTensors (sharded) \| SafeTensors (sharded) \|
	\| Precision \| BF16 uniform \| Mixed 5/6/8/8-bit affine + BF16 \|

	## All Variants

	\| Repo \| Format \| Size \| Decode (tok/s) \|
	\|---\|---\|---\|---\|
	\| [Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx) \| UD-Q3_K_XL \| 17 GB \| 111.6 \|
	\| [Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx) \| MXFP4 \| 20 GB \| 107.8 \|
	\| [Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx) \| UD-Q4_K_XL \| 22 GB \| 102.3 \|
	\| [Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx) \| NVFP4 \| 23 GB \| 94.6 \|
	\| [Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx) (this model) \| UD-Q5_K_XL \| 26 GB \| 95.4 \|
	\| [Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx) \| UD-Q6_K_XL \| 31 GB \| 93.1 \|
	\| [Brooooooklyn/Ornith-1.0-35B-UD-Q8_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q8_K_XL-mlx) \| UD-Q8_K_XL \| 36 GB \| 91.5 \|
	\| [Brooooooklyn/Ornith-1.0-35B-mxfp8-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-mxfp8-mlx) \| MXFP8 \| 36 GB \| 84.8 \|

	Benchmarked on a cool Apple M5 Max: median decode throughput over three 512-token generations, with a 60-second idle GPU cooldown after every generation. (Sustained decode on Apple Silicon is thermally sensitive — back-to-back benchmarking on a hot chip can understate throughput by 20–30%, so every model here was measured from a comparable cool start.)

	## Performance

	Steady-state decode: 95.4 tok/s (1.5x vs BF16) on Apple M5 Max. Decode is memory-bandwidth bound on Apple Silicon — fewer bytes per token directly translates to higher throughput. The MoE architecture activates only 8 of 256 experts per token (~3B active out of 35.9B total), so the active-weight footprint streamed per token is what matters.

	## Output Quality

	Decoded-text quality was verified against the BF16 reference with a multi-judge review of the actual generated output (not a heuristic): a 4-turn factual chat plus a Python `is_balanced()` bracket-matching task. This `UD-Q5_K_XL` build produced coherent prose, correct facts, and a correct implementation — no runaway generation, repetition loops, or stray tokens — on par with full precision. (The 2-bit tier is intentionally excluded from this collection: it was the only width that showed coherence breakdown.)

	## Per-Tensor Quantization

	\| Weight \| Bits \| Rationale \|
	\|---\|---\|---\|
	\| `embed_tokens` \| 8-bit affine \| KLD ~0.15 — very low sensitivity \|
	\| `lm_head` \| 8-bit affine \| KLD ~0.05 — safest tensor \|
	\| `self_attn.q/k/v_proj` \| 8-bit affine \| KLD ~1.5–2.9 — attention-sensitive \|
	\| `linear_attn.in_proj_qkv/z` \| 8-bit affine \| KLD ~2.9 — SSM input gates \|
	\| `self_attn.o_proj` \| 8-bit affine \| KLD ~1.5; row-independent qmv for T=0 exactness \|
	\| `linear_attn.out_proj` \| 8-bit affine \| KLD ~6.0 — worst tensor; kept high \|
	\| `linear_attn.in_proj_a/b` \| 8-bit affine \| tiny low-rank GDN projections \|
	\| `switch_mlp.down_proj` \| 6-bit affine \| "slightly more sensitive" than other FFN \|
	\| `switch_mlp.gate_proj/up_proj` \| 5-bit affine \| bulk of the expert budget \|
	\| Router gates (`mlp.gate`, `shared_expert_gate`) \| 8-bit affine \| MoE routing accuracy \|
	\| GDN params (`A_log`, `dt_bias`) \| bf16 \| state-space dynamics \|
	\| `vision_tower.` \| bf16* \| vision encoder kept full precision \|

	## Quantization Strategy

	Built on [Unsloth Dynamic 2.0](https://unsloth.ai/docs/models/qwen3.5/gguf-benchmarks) per-tensor KLD analysis: sensitive layers (attention/SSM inputs, down_proj, embeddings/head) get higher bits, while the bulk of FFN expert weights are quantized to the base width. `self_attn.o_proj`, `linear_attn.out_proj`, the split low-rank GDN projections (`in_proj_a/b`) and the MoE router gates are pinned to 8-bit affine (group_size 64). GatedDeltaNet state-space parameters and the vision encoder stay bf16.

	> Note: These ornith quants apply the Unsloth bit allocation without imatrix AWQ pre-scaling — ornith has no published imatrix, so the attention/SSM channels are quantized directly. Expect a small quality gap versus an imatrix-calibrated build at the lowest bit widths.

	## Architecture

	\| Parameter \| Value \|
	\|---\|---\|
	\| Total parameters \| 35.9B (~3B active per token) \|
	\| Hidden size \| 2,048 \|
	\| Layers \| 40 (30 linear GatedDeltaNet + 10 full attention) \|
	\| Attention heads \| 16 (2 KV heads, GQA 8:1) \|
	\| Head dimension \| 256 \|
	\| Experts \| 256 per MoE layer, top-8 routing \|
	\| Vocab size \| 248,320 \|
	\| Vision \| yes (Qwen3.5-VL vision tower, kept bf16) \|
	\| Max context \| 262,144 tokens \|

	## Usage

	```typescript
	import { loadSession } from '@mlx-node/lm';

	const session = await loadSession('./Ornith-1.0-35B-UD-Q5_K_XL-mlx');

	for await (const event of session.sendStream('Write a Python function to merge two sorted lists.', {
	config: { maxNewTokens: 2048, temperature: 0.6, reasoningEffort: 'low' },
	})) {
	if (!event.done) process.stdout.write(event.text);
	}
	```

	## How It Was Made

	```bash
	mlx convert \
	-i Ornith-1.0-35B \
	-o Ornith-1.0-35B-UD-Q5_K_XL-mlx \
	-q --q-recipe unsloth --q-bits 5
	```

	The Unsloth recipe's per-tensor bit tiers were applied without imatrix AWQ (no native ornith imatrix). 7-bit tiers are snapped up to 8-bit (MLX affine supports 2/3/4/5/6/8-bit).

	## Acknowledgments

	- [Unsloth](https://unsloth.ai) — Per-layer KLD bit-allocation strategy ([Dynamic 2.0](https://unsloth.ai/docs/models/qwen3.5/gguf-benchmarks))
	- [DeepReinforce](https://deep-reinforce.com/ornith.html) — For the Ornith-1.0 model family
	- [Qwen Team](https://huggingface.co/Qwen) — For the Qwen3.5 base architecture
	- [Apple MLX](https://github.com/ml-explore/mlx) — For the Metal-accelerated ML framework

	## License

	[MIT](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE) (inherited from base model).