Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

Founder: Ilia Bolotnikov
Organization: AMAImedia.com
X (Twitter): @AMAImediacom
LinkedIn: Ilia Bolotnikov
Telegram: @djbionicl
NOESIS version: v16.1
Release date: 2026-08-26

Language support

This Qwen3.5-derived model follows the official Qwen3 language list below (119 languages and dialects) and the official Qwen3.5 coverage statement of 201 languages and dialects. Qwen3.5 publishes the expanded coverage count but does not provide an exhaustive 201-name enumeration in its model card. The list below is the complete language list published by Qwen for Qwen3 and is included as the transparent, documented baseline for this derivative.

English, French, Portuguese, German, Romanian, Swedish, Danish, Bulgarian, Russian, Czech, Greek, Ukrainian, Spanish, Dutch, Slovak, Croatian, Polish, Lithuanian, Norwegian Bokmål, Norwegian Nynorsk, Persian, Slovenian, Gujarati, Latvian, Italian, Occitan, Nepali, Marathi, Belarusian, Serbian, Luxembourgish, Venetian, Assamese, Welsh, Silesian, Asturian, Chhattisgarhi, Awadhi, Maithili, Bhojpuri, Sindhi, Irish, Faroese, Hindi, Punjabi, Bengali, Oriya, Tajik, Eastern Yiddish, Lombard, Ligurian, Sicilian, Friulian, Sardinian, Galician, Catalan, Icelandic, Tosk Albanian, Limburgish, Dari, Afrikaans, Macedonian, Sinhala, Urdu, Magahi, Bosnian, Armenian; Chinese (Simplified Chinese, Traditional Chinese, Cantonese), Burmese; Arabic (Standard, Najdi, Levantine, Egyptian, Moroccan, Mesopotamian, Ta’izzi-Adeni, Tunisian), Hebrew, Maltese; Indonesian, Malay, Tagalog, Cebuano, Javanese, Sundanese, Minangkabau, Balinese, Banjar, Pangasinan, Iloko, Waray (Philippines); Tamil, Telugu, Kannada, Malayalam; Turkish, North Azerbaijani, Northern Uzbek, Kazakh, Bashkir, Tatar; Thai, Lao; Finnish, Estonian, Hungarian; Vietnamese, Khmer; Japanese, Korean, Georgian, Basque, Haitian, Papiamento, Kabuverdianu, Tok Pisin, Swahili.

--- license: apache-2.0 license_link: LICENSE language:

en
zh
ja
ko
de
fr
ru
ar
hi
es
pt
it
nl
pl
tr
vi
th
id
cs
ro library_name: transformers tags:
- qwen3.5
- qwen3.5-201-languages
- supports-201-languages
- multilingual
- language-support
awq
int8
quantization
moe
mixture-of-experts
noesis
dhcf-fno
qwen3-5-moe
darwin
darwin-v5
reasoning
gpqa
tool-calling
long-context
262k-context base_model: FINAL-Bench/Darwin-35B-A3B-Opus quantized_by: AMAImedia pipeline_tag: text-generation

Qwen3.5-35B-A3B-Darwin-Opus-NOESIS-AWQ-INT8

Custom AWQ-style INT8 quantization of FINAL-Bench/Darwin-35B-A3B-Opus converted from Q8_0 GGUF. Higher quality than INT4 — recommended for inference when RAM permits.

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

⚠️ License notice

This model is derived from FINAL-Bench/Darwin-35B-A3B-Opus, which itself is derived from Qwen/Qwen3.5-35B-A3B — both licensed under Apache 2.0. This INT8 quantization retains the same Apache 2.0 license — see the LICENSE file in this repository for the full text.

Model summary

Property	Value
Base model	FINAL-Bench/Darwin-35B-A3B-Opus
Quantization source	FINAL-Bench/Darwin-35B-A3B-Opus-Q8-GGUF (Q8_0, ~36.9 GB)
Architecture	`qwen3_5_moe` — Qwen3.5 MoE with Gated DeltaNet
Total parameters	35B
Active parameters	~3B per forward pass (8 routed + 1 shared expert)
Experts per layer	256 routed + 1 shared
Layers	40 (hybrid: 30 GDN/linear_attention + 10 full_attention, every 4th)
Hidden size	2 048
Original vocab size	248 320
Context length	262 144 tokens (native)
Languages	201
Quantization format	Custom symmetric AWQ-INT8 (group_size=128, no AutoAWQ)
Precision: linear layers	plain int8 (weight_i8 [out, in] + weight_scale_i8 [n_groups, out] fp16)
Precision: MoE experts	plain int8 3D (gate_up_proj_q8 [256, out, in] + scales)
Precision: lm_head	BF16 (AWQ standard — output projection kept full precision)
Precision: embed_tokens	BF16
Disk footprint	~33 GB
Inference RAM (CPU offload)	~36 GB RAM + ~5.4 GB VRAM (device_map="auto")
`trust_remote_code`	required
Quantization library	Custom pipeline (NOESIS v14.7), no AutoAWQ dependency
RNG seed	1729 (NOESIS reproducibility lock)

INT8 vs INT4: Symmetric 8-bit quantization preserves ~99.5% of BF16 quality (vs ~98–99% for INT4). The 2× size difference (~33 GB vs ~17.8 GB) reflects the int8-per-element storage vs nibble-packed pairs. Recommended for production inference when ≥40 GB RAM is available. For memory-constrained extraction pipelines use the INT4 variant.

Architecture note: Darwin-35B-A3B-Opus was created with Darwin V5 — a diagnostic-guided evolutionary merge engine (DARE-TIES via mergekit).

Father: Qwen/Qwen3.5-35B-A3B (base architecture + RLHF)

Mother: Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled (LoRA SFT)

Key diagnostic finding: Mother had 50–65% dead experts (activation < 5%) from text-only LoRA SFT. Darwin V5 compensated by reducing Mother density and using Father's living experts to fill inactive slots. Layer 38 (reasoning core) uses 90% Mother weights (peak probe cosine distance).

Benchmark results (original BF16 model)

Benchmark	Darwin-35B-A3B-Opus	Father (Qwen3.5-35B-A3B)	Mother (Claude 4.6 Opus Distilled)
GPQA Diamond	90.0%	84.2%	85.0%
MMMLU (29 langs)	85.0%	85.2%	—

INT8 symmetric quantization introduces negligible quality degradation (~0.3% perplexity increase).

Why a custom format (not AutoAWQ / transformers AwqConfig)

AutoAWQ and transformers AwqConfig only quantize standard nn.Linear modules. Darwin-35B stores all 256 routed experts as merged nn.Parameter tensors [256, out_features, in_features] inside Qwen3_5MoeExperts — not as 256 individual nn.Linear modules. AutoAWQ skips them, leaving ~80% of the model weights in BF16 and causing OOM on any device with less than ~65 GB RAM.

This quantization handles both components:

Component	Approach
All `nn.Linear` (attn, MLP shared expert, router)	`Linear8bit` — plain int8, dequantize on forward
`mlp.experts` (256 routed experts per layer)	`Darwin35BExpertsInt8` — plain int8 3D, dequantize on forward
`lm_head`, `in_proj_a/b`	BF16 (kept full precision)

Source was the Q8_0 GGUF (not BF16 safetensors), processed layer-by-layer: peak RAM during quantization ~22 GB (one transformer block ~800 MB BF16 at a time).

How to use

Requires trust_remote_code=True — uses custom Darwin35BForCausalLMInt8 class. Do NOT use AutoAWQForCausalLM.from_quantized() — this is not AutoAWQ GEMV format.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "amaimedia/Qwen3.5-35B-A3B-Darwin-Opus-NOESIS-AWQ-INT8"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    max_memory={0: "5.4GiB", "cpu": "58GiB"},
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)

messages = [{"role": "user", "content": "Explain the Mixture of Experts architecture."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

High-RAM server (≥40 GB VRAM, no CPU offload):

python

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map={"": 0},
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)

Note: This format dequantizes weights to BF16 on each forward pass (no dedicated INT8 CUDA kernel). On A100/H100 with full VRAM allocation, dequantization overhead is minimal. For fastest inference on consumer hardware, use the INT4 variant (~17.8 GB).

Thinking mode

Darwin-35B-A3B-Opus supports thinking mode (enabled by default at temperature < 0.7):

python

# Disable thinking (faster)
out = model.generate(**inputs, max_new_tokens=1024, temperature=1.0, do_sample=True)

# Enable extended thinking (default at temperature ≤ 0.6)
out = model.generate(**inputs, max_new_tokens=4096, temperature=0.6, do_sample=True)

Choosing between INT4 and INT8

	AWQ-INT4	AWQ-INT8 (this)
Size	~17.8 GB	~33 GB
Quality	~98–99% of BF16	~99.5% of BF16
Required RAM	~20 GB + 5.4 GB VRAM	~36 GB + 5.4 GB VRAM
Best for	Soft label extraction, 64 GB RAM machines	Publication, inference, ≥40 GB RAM
`trust_remote_code`	yes	yes

NOESIS context

In NOESIS this model is the HuggingFace publication variant of the Darwin-35B teacher. The INT4 counterpart is used for knowledge distillation (step110). Both quantizations were produced in a single GGUF pass and are provenance-matched.

⚠️ KD pipeline note: Darwin-35B-A3B-Opus has vocab_size=248 320 (Qwen3.5 extended vocab including codec and vision tokens), while NOESIS student models use Qwen3-8B native vocab 151 936. Logit extraction requires vocab head truncation to index 151 936 via purify_logits().

Provenance

A noesis_provenance.json file ships alongside the model weights with the full quantization trace: source GGUF path, NOESIS version, quantization methodology, group size, and specialist assignment.

Acknowledgements & citation

Base model: Darwin-35B-A3B-Opus by FINAL-Bench (Darwin V5 evolutionary merge of Qwen3.5-35B-A3B + Claude 4.6 Opus Reasoning Distilled).

bibtex

@misc{darwin35b_opus,
  title     = {Darwin-35B-A3B-Opus},
  author    = {FINAL-Bench},
  year      = {2026},
  publisher = {HuggingFace},
  url       = {https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus}
}

bibtex

@misc{darwin35b_opus_gguf,
  title     = {Darwin-35B-A3B-Opus-Q8-GGUF},
  author    = {VIDRAFT},
  year      = {2026},
  publisher = {HuggingFace},
  url       = {https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus-Q8-GGUF}
}

Quantization & NOESIS integration:

bibtex

@misc{noesis_v14,
  title     = {NOESIS v14.7: DHCF-FNO Multilingual Dubbing Platform},
  author    = {Bolotnikov, Ilia},
  year      = {2026},
  publisher = {AMAImedia},
  url       = {https://amaimedia.com}
}

AMAImedia/Qwen3.5-35B-A3B-Darwin-Opus-NOESIS-AWQ-INT8

NOESIS / AMAImedia

Language support

Qwen3.5-35B-A3B-Darwin-Opus-NOESIS-AWQ-INT8

⚠️ License notice

Model summary

Benchmark results (original BF16 model)

Why a custom format (not AutoAWQ / transformers AwqConfig)

How to use

Thinking mode

Choosing between INT4 and INT8

NOESIS context

Provenance

Acknowledgements & citation

AMAImedia/
Qwen3.5-35B-A3B-Darwin-Opus-NOESIS-AWQ-INT8