# Qwen3.8 Flash Next E384 FP4 V2

URL: https://interfaze.ai/models/autotrustqwen38-flash-next-e384-fp4-v2

[All models](https://interfaze.ai/models)

Qwen3.8 Flash Next E384 FP4 V2 by autotrust, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.

## Comparison

| Feature | Qwen3.8 Flash Next E384 FP4 V2 | Interfaze |
| --- | --- | --- |
| Input Modalities | text, image, video | image, text, audio, video, document |
| Native OCR | No | Yes |
| Long Document Processing | No | Yes |
| Language Support | 8 partial | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | No | Yes |
| Guardrail Controls | Yes | Yes |
| Context Input Size | 1M | 1M |
| Tool Calling | Yes | Tool calling supported + built in browser, code execution and web search |

### Scaling

| Feature | Qwen3.8 Flash Next E384 FP4 V2 | Interfaze |
| --- | --- | --- |
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |

[Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)

View model card on [Hugging Face](https://huggingface.co/autotrust/Qwen3.8-Flash-Next-E384-FP4-V2)

A compact build of [nvidia/Qwen3.8-Flash-Next-FP4-Local](https://huggingface.co/nvidia/Qwen3.8-Flash-Next-FP4-Local) found by **Neural Architecture Search (NAS)** over the routed-expert configuration: it keeps **384 of the 512 routed experts** in every decoder MoE layer and in the MTP layer.

Unchanged from the original:

-   top-10 routing and the shared experts;
-   attention, the n-gram PLE table, the vision tower and the tokenizer.

This is an unofficial derivative, not produced or endorsed by Alibaba or NVIDIA.

|  | original (512 experts) | E384 |
| --- | --- | --- |
| weights | 102.14 GB = 95.12 GiB | 85.66 GB = 79.78 GiB (−15.35 GiB, −16.1 %) |
| routed experts / layer (decoder + MTP) | 512 | 384 |
| active experts / token | 10 + shared | 10 + shared |

Full merged checkpoint of the E384 FP4 model after GRPO-style reinforcement learning with a LoRA adapter. **This is a complete model, not an adapter**: all 21 weight shards, the tokenizer, configs and MTP files are included. It is an unofficial derivative and is not endorsed by Alibaba or NVIDIA.

## Serving

Validated with vLLM 0.31 on one B200. The included `vllm_patch/sitecustomize.py` is needed for this checkpoint's FP4/CSF/PLE weight layout. From this directory:

```
export PYTHONPATH="$PWD/vllm_patch${PYTHONPATH:+:$PYTHONPATH}"
vllm serve . --served-model-name e384-rl --port 8000 \
  --tensor-parallel-size 1 --dtype bfloat16 --kv-cache-dtype fp8 \
  --quantization modelopt_mixed --mamba-cache-mode align \
  --enable-prefix-caching --enable-chunked-prefill \
  --max-model-len 72000 --max-num-seqs 128 --gpu-memory-utilization 0.90 \
  --reasoning-parser qwen3 --tool-call-parser qwen3_xml --enable-auto-tool-choice
```

`serve_vllm.sh` is the equivalent portable launcher. The model was benchmarked through this serving path, including the FP8 KV cache and the Qwen reasoning/tool parsers.

## Training and checkpoint contents

-   Three GRPO-style LoRA updates with verifiable rewards; the final round targets short-budget CVSS completion and structured findings emission.
-   LoRA rank 32, alpha 64. The routed experts, router, shared expert and PLE are frozen.
-   The GDN projection deltas are folded at full precision and those projections are stored as BF16; the corresponding entries are removed from `quantization_config.quantized_layers`. Other model tensors retain the base checkpoint format.
-   The final adapter was merged into the weights before this repository was created. No adapter loading step is needed.

## Full benchmark results

Same benchmark harness and serving settings for all rows. These are single runs; GPQA has only 198 questions and is correspondingly noisy. AIME 2026 uses 30 problems x 4 samples with xhigh reasoning and a 64k generation budget. Base numbers are the previously published reference numbers, not a rerun.

| benchmark | base reference | this model |
| --- | --- | --- |
| GPQA-Diamond (low, 32k) | 77.3 | 75.76 |
| MMLU (14,042) | 86.9 | 87.37 |
| C-Eval val (1,346) | 89.0 | 89.97 |
| AIME 2026 (xhigh, 64k) | 93.3 | 95.0 |
| HumanEval (164, greedy) | 97.6 | 98.78 |
| MMMU val (900) | 79.4 | 78.22 |
| tool calling (800) | — | 77.88 |

Detailed per-task counts and truncation statistics are in `benchmark_results.json`.

### AIME reasoning length

Compared with the preceding RL checkpoint on the same 120 AIME samples, total completion tokens fell 2.05% (19,897 to 19,490 per answer on average), while accuracy rose from 92.5 to 95.0. The median was essentially unchanged (16,528 to 16,675 tokens); the reduction came mainly from the long tail (P90 58,272 to 45,339) and fewer 65,536-token truncations (9 to 6). `completion_tokens` includes both the reasoning trace and the final answer.

## Behavior notes and limitations

On the same training-prompt evaluation used during the final RL round, CVSS3 completion within a 2,200 token budget rose from 39% to 70%, CVSS4 from 18% to 60%, and structured-findings emission reward from 0.609 to 0.917. Math and guard rewards did not degrade in that evaluation. These are training-prompt measurements, not an independent behavior benchmark.

**CVSS arithmetic is still not reliable**: among completed answers, exact agreement with the reference implementation was about 4.5% for CVSS3 and 4.2% for CVSS4 in that evaluation. This checkpoint should not be described as having fully fixed CVSS scoring. See `behavior_results.json` for the detailed comparison.

## Want more deterministic results?

[Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)