A text-only sparse-MoE release candidate built as a practical local alternative to Qwen3.5-4B. It has 4.0B total parameters and 3.0B active parameters per token. The initialization preserves Qwen3.5-2B behavior, while adding output-neutral trainable capacity for later Qwen3.5-4B distillation.

This is an independently measured research release. It is not an official Qwen model and does not include vision.

Architecture

Property	Value
Total parameters	3,995,901,760
Active parameters/token	2,995,560,256
Transformer layers / hidden size	24 / 2,048
Experts / selected per token	2 / 1
Shared / routed intermediate width	6,912 / 6,784
Vision tower	No
Weight dtype	BF16

Each MoE layer initially computes one half of the original Qwen3.5-2B dense MLP through the shared path and one half through the selected routed expert. The two routed experts begin functionally identical. Additional neurons have random gate/up projections and zero down projections, making them output-neutral but trainable. Exact conversion metadata is in conversion_manifest.json.

Evaluation

All reported results were produced locally on an Apple M4 with 32GB unified memory. Raw JSON reports are included in evaluation/.

Chat and sentence generation

The fixed gate contains 60 prompts: 10 each in Korean, English, Chinese, Japanese, Spanish, and German. It covers facts, arithmetic, translation, instruction following, and free-form sentence generation.

Result	Score
Non-degenerate/correct automatic checks	60 / 60
Languages meeting the gate	6 / 6

Six chemical-formula answers used the correct Unicode spelling H₂O; the scorer normalizes Unicode subscripts before comparison.

Multilingual held-out LM loss

Four held-out FineWeb/FineWeb2 documents per language, 128 tokens per document:

Model	Mean loss	Relative to Qwen3.5-4B
Qwen3.5-4B	2.9399	1.000x
This model	3.2085	1.091x
Qwen3.5-2B	3.2085	1.091x

Standard benchmark development subset

EleutherAI lm-evaluation-harness==0.4.12, zero-shot, BF16, first 100 examples per task. These limited results are development indicators, not full-task benchmark claims.

Model	ARC-Easy acc_norm	HellaSwag acc_norm	Mean
Qwen3.5-4B	0.81	0.68	0.745
This model	0.73	0.62	0.675

The subset mean is 90.6% of the Qwen3.5-4B teacher mean.

Local service gate

The included FastAPI service completed 20/20 consecutive non-streaming POST /v1/chat/completions requests:

Metric	Value
Successful requests	20 / 20
Mean latency	2.60 s
p95 latency	3.57 s
MPS allocated memory	7.62 GB

Requests generated up to 16 new tokens. See evaluation/openai_service_20.json.

Transformers usage

Use Transformers 5.13.0 or another version that provides Qwen3_5MoeForCausalLM:

python

import torch
from transformers import AutoTokenizer, Qwen3_5MoeForCausalLM

model_id = "sepsy070716/Qwen3.5-4B-A3B-Student-v2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = Qwen3_5MoeForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
)

messages = [{"role": "user", "content": "대한민국의 수도는 어디인가요?"}]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    enable_thinking=False,
    return_tensors="pt",
    return_dict=True,
).to(model.device)
output = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Reproduction and service

research_code/ contains the converter, multilingual loss comparison, 60-prompt gate and scorer, plus the local OpenAI-compatible service and its 20-request test. The service implements GET /health, GET /v1/models, and non-streaming POST /v1/chat/completions.

Limitations

Current quality is inherited primarily from Qwen3.5-2B; the extra capacity has not yet received large-scale continued pretraining or teacher distillation.
The 100-example ARC-Easy/HellaSwag figures are small development subsets and have substantial sampling uncertainty. Run the full tasks before making publication or production claims.
This model is text-only and cannot replace the original model's vision path.
The included server is a single-process local research server. It has no authentication, TLS, streaming, tool calling, or multi-worker support.
Apply the same safety, bias, privacy, and factuality evaluation required for any deployment of the upstream Qwen models.

License and attribution

Released under Apache-2.0, following the included upstream license. Derived from Qwen3.5-2B weights and evaluated against Qwen3.5-4B. Qwen model names and trademarks belong to their respective owners.