NovaeonStudio/Occamy-1.0-oQ8-fp16-mtp

Occamy-1.0 · oQ8-fp16-mtp — a Novaeon.Studio build

A fast, super-agentic local worker for Apple Silicon. This is an oMLX oQ8 (near-uniform 8‑bit, router fp16) quantization of Accio-Lab/occamy-1.0 — the 35B‑A3B agentic co‑worker — repacked for the Mac and shipped with the official experimental MTP head merged in. Built, tuned, and benchmarked on an Apple M5 Max (128 GB) by Novaeon.Studio.

Why this build exists: we run local agents on Apple Silicon and wanted Occamy's tool‑use reliability at 8‑bit fidelity, in oMLX‑native format, with a documented optimal serving profile — not a generic dump. Everything below is measured on our hardware, not copied.

Base model	Accio-Lab/occamy-1.0 (Apache‑2.0)
Architecture	Qwen3.5/3.6‑family MoE + vision encoder · 35B total / ~3B active · 256 experts (8 routed + 1 shared) · 40 layers
Quantization	oQ8, group size 64, float16 scales/non‑quant weights · 6.8→8.6 effective bpw · ~38 GB on disk
MTP head	Official occamy-1.0-MTP grafted (language_model.mtp.*) — see note below
Context	262,144 native (SFT 131,072) · vision preserved
Engine	oMLX (Apple MLX) — VLM engine

---

Highlights

• Super‑agentic. 6/6 on our controlled tool‑use probe suite (tool selection, parallel calls, sequential tool chains, argument fidelity, correct abstention, no hallucinated tools).
• 8‑bit fidelity. Near‑uniform 8‑bit with fp16 router — the highest‑fidelity published Apple‑Silicon Occamy build.
• Tuned for speed. Ships a documented optimal oMLX profile (ANE‑prefill + TurboQuant‑KV) that sustains throughput far into long context.
• Vision intact. Multimodal (text + image → text); the vision tower is preserved from the base.

---

Measured benchmarks (Apple M5 Max 128 GB · oMLX)

All numbers below were measured on our hardware, on these exact weights, with the seat isolated (no other load) using the optimal profile.

Decode throughput vs context

Prompt context	~0	~3.9k	~7.9k	~15.9k	~31.9k	~64.7k
Decode (tok/s)	92	86	82	76	58	43
TTFT (s)	0.29	0.92	0.80	5.0¹	1.6	49¹

_{¹ First large‑prefill compile spikes; steady‑state prefill is fast. Cold load ≈ 18–36 s (39 GB weights).}

Agentic & tool‑use — 35B‑A3B open agentic class

Occamy‑1.0 is top‑tier for tool‑use and function‑calling among same‑size (35B‑A3B) open agentic MoE models. The numbers below are the published Accio‑Lab benchmark table. Our retired Novaeon seat was a Qwen3.6‑35B‑A3B tune, so its base Qwen3.6‑35B‑A3B is included as its reference point:

Our own probe on this build — 6/6 (temp 0): tool selection, parallel tool calls, sequential tool chains, argument fidelity, abstention when no tool is needed, and no hallucinated tools. This bespoke probe was only run on this build (6/6) and our retired general seat (5/6), so it is not comparable to the public models above — the retired seat is shown purely as a local reference.

Internal 6‑probe detail (this build vs retired seat)

- **IFEval (ours, this build): 84.58 avg** — measured locally against these quantized weights (thinking off), scored with the official IFEval verifier (541 prompts, 834 instructions).

IFEval (this build)	prompt‑strict	prompt‑loose	inst‑strict	inst‑loose	avg
Occamy‑1.0 oQ8‑fp16‑mtp	79.67	83.36	86.21	89.09	84.58

_{Base card reports IFEval 91.53; the gap reflects 8‑bit quantization plus our thinking‑off / no‑CoT eval setup. Number is real and reproducible on these weights.}

---

Optimal oMLX settings (figured out empirically)

We swept the tuning levers on this build. Result — because the grafted MTP head does not accelerate decode under oQ8 (below), ANE‑prefill wins here (there is no MTP dispatch overhead to fight), and TurboQuant‑KV keeps long‑context decode high:

Setting	Value	Why
qwen35_ane_prefill_enabled	true	+~12% sustained long‑context decode; best TTFT at long context
qwen35_ane_prefill_dual_ane / gdn / cpu_enabled	true	dual‑ANE + GDN + CPU prefill assist
turboquant_kv_enabled / turboquant_kv_bits	true / 8	holds decode up as context grows
qwen35_oq_a8_enabled	false	A8 collapsed long‑context decode in testing
mtp_enabled	false	grafted head is inert under oQ8 (see note) — off avoids wasted draft compute
moe_expert_offload_enabled	false	keep experts resident (128 GB is ample)

Drop‑in ~/.omlx/model_settings.json entry

{
  "max_context_window": 262144,
  "turboquant_kv_enabled": true,
  "turboquant_kv_bits": 8.0,
  "turboquant_skip_last": true,
  "qwen35_ane_prefill_enabled": true,
  "qwen35_ane_prefill_sequence_length": 2048,
  "qwen35_ane_prefill_dual_ane": true,
  "qwen35_ane_prefill_gdn": true,
  "qwen35_ane_prefill_cpu_enabled": true,
  "qwen35_oq_a8_enabled": false,
  "moe_expert_offload_enabled": false,
  "mtp_enabled": false
}

On the MTP head: we merged Accio's official experimental occamy-1.0-MTP head (converted to the MLX language_model.mtp.* layout). oMLX recognizes it (mtp_compatible: true), but under oQ8 speculative acceptance is negligible — MTP on/off decode is identical in our A/B. Accio notes the head "requires the same decode kernels for verification" and validated it only on BF16/NVFP4, so the oQ8 verifier rejects nearly every draft. The head is shipped for correctness and future‑runtime support; we serve with mtp_enabled: false.

---

Quickstart

# oMLX (recommended, Apple Silicon)
omlx serve NovaeonStudio/Occamy-1.0-oQ8-fp16-mtp --port 8000
# then hit the OpenAI-compatible endpoint at http://127.0.0.1:8000/v1

# mlx-vlm
pip install -U mlx-vlm
python -m mlx_vlm.generate --model NovaeonStudio/Occamy-1.0-oQ8-fp16-mtp \
  --max-tokens 4096 --temperature 1.0 --top-p 0.95 \
  --prompt "Search the repo for where payment-API errors get swallowed, then propose a fix."

Recommended inference parameters (from the base card)

temperature 1.0 · top_p 0.95 · top_k 20 · presence_penalty 1.5 · reasoning_parser qwen3 · tool_call_parser qwen3_coder. Thinking is on by default (<think>…</think>, returned in reasoning_content); pass enable_thinking: false for fast, plain instruction‑following.

---

How it compares in its class (35B‑A3B)

Against the other 35B‑A3B open models, Occamy‑1.0 leads its size class on the core agentic / co‑work benchmarks and is competitive on tool‑calling, coding, and instruction‑following.

Full table (best in each row in bold; this build is a quantization of Occamy-1.0, so the Occamy column reflects the base weights — our locally‑measured IFEval 84.6 and agentic 6/6 above corroborate the quant holds):

Benchmark	Occamy‑1.0	Qwen3.6‑35B‑A3B	Agents‑A1	Nex‑N2‑mini	BigBang‑1.0	Ornith‑1.5
Claw‑Eval (avg)	82.20	69.50	69.90	66.60	63.50	64.40
Claw‑Eval (Pass³)	71.40	54.80	41.70	37.00	40.20	48.70
WildClawBench	49.16	40.40	30.73	30.31	32.87	45.91
CommerceAgentBench	37.38	19.60	9.30	16.80	30.80	37.40
τ³‑Bench (Banking)	37.10	11.90	7.20	25.80	10.30	21.70
AutomationBench (Pass¹)	27.60	7.50	2.20	5.70	14.80	18.50
AutomationBench (partial)	69.10	39.40	14.70	27.90	47.40	58.00
OfficeQA Pro	48.10	39.10	23.30	46.60	43.60	59.40
BFCL v4 (tool calling)	65.40	63.19	57.23	62.81	57.86	68.51
VitaBench	41.75	34.25	37.00	26.25	46.00	40.25
Terminal‑Bench 2.1	59.00	49.50	41.60	60.70*	33.70	67.80*
IFEval	91.53	86.90	91.60	91.60	90.50	81.80

_{Numbers reproduced from the Accio‑Lab Occamy‑1.0 benchmark table, same‑size class. * official model‑card / Artificial Analysis result. Larger models (GPT‑5.6 Sol, Qwen3.8‑Max, DeepSeek V4, GLM‑5.2) are out of this size class and score higher on several tasks — see the base card. BFCL v4 and Terminal‑Bench were not re‑run locally on this quant.}

---

Attribution & license

• Base model: Accio-Lab/occamy-1.0 — Apache‑2.0. Project: accio-lab.github.io/occamy · Paper: arXiv:2609.11977 · Training framework: Dressage.
• MTP head: Accio-Lab/occamy-1.0-MTP (experimental).
• This quantization & serving profile: Novaeon.Studio, 2026. Released under Apache‑2.0, same as the base.

This is an independent community quantization. It is not endorsed by Accio‑Lab. All credit for the model's capabilities belongs to the Occamy‑1.0 authors.

@misc{novaeon2026occamyoq8,
  title  = {Occamy-1.0 oQ8-fp16-mtp: an oMLX build for Apple Silicon},
  author = {Novaeon.Studio},
  year   = {2026},
  note   = {Quantization of Accio-Lab/occamy-1.0},
  url    = {https://huggingface.co/NovaeonStudio/Occamy-1.0-oQ8-fp16-mtp}
}

_{novæon — digital business architecture + AI · novaeon.studio}