base_model: orcarouter/Qwen3.8-Flash-Next-Uncensored
base_model_relation: quantized
library_name: mlx
pipeline_tag: image-text-to-text
license: other
license_name: qwen-community-1.0
license_link: LICENSE
tags:
- omlx
- mlx
- qwen4
- mtp
- vision
- tool-calling
- uncensored
- abliterated
Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp
An oMLX-native oQ5e quantization oforcarouter/Qwen3.8-Flash-Next-Uncensored,
the BF16 abliterated build of Qwen3.8-Flash-Next. Targets a 128 GB Apple
Silicon Mac and preserves the vision tower, the MTP head, and the checkpoint's
native 262,144-token architecture setting.
For the abliteration method, refusal-direction details, and MTP-consistency
notes, see the source model card linked above. This repository only documents
the quantization.
Companion build: LMLiutenant/Qwen3.8-Flash-Next-Uncensored-oQ6e-mtp
(higher precision, ~6.9 bpw).
Nature of this model
This is an uncensored (abliterated) model: the source weights have had their
refusal direction removed, so it will attempt most requests without the
safety refusals present in the official Qwen release. It has no added
guardrails. You are responsible for how you use it and for complying with the
license and applicable law. Do not expose it to untrusted input in an agentic
setup without your own safeguards; with no refusal behaviour, it will not push
back on injected instructions.
Quantization
| Property | Value |
|---|---|
| Base model | orcarouter/Qwen3.8-Flash-Next-Uncensored |
| Quantization | oQ5e |
| Quantizer | oMLX 0.6.4 |
| Enhanced / imatrix mode | Yes |
| Nominal group size | 64 |
| Non-quantized dtype | BF16 |
| MTP preserved | Yes |
| Vision preserved | Yes |
| Sensitivity model | jedisct1/Qwen3.8-Flash-Next-Uncensored-oQ4e-100K-MTP |
The oQ5e weights were quantized directly from the abliterated BF16 source. The
sensitivity model was used only to guide mixed-precision allocation; its
quantized weights are not the source of this model. It was chosen for matched
abliterated lineage with the source. Nominal group size was 64; oQ mixed-precision
may use different effective settings for selected tensors.
Hardware and memory
Qwen3.8-Flash-Next contains a very large N-gram/PLE component. With SSD N-gram
Offload it does not all stay resident in unified memory, which is what makes a
model this size practical on a 128 GB machine. Long-context and KV-cache use
raise memory further with context length.
Tested on a MacBook Pro, Apple M4 Max, 128 GB, oMLX, with SSD N-gram Offload
enabled. Peak MLX allocation (weights + KV + activations), measured in oMLX with SSD
N-gram Offload on: ~88 GB at 4K context, ~92 GB at 128K. These are
process-level allocator peaks, not total-system memory.
Recommended oMLX settings
For a 128 GB Apple Silicon Mac:
- SSD N-gram Offload: ON
- Lightning MTP: ON for chat/reasoning; consider OFF for coding agents
Serve via oMLX's OpenAI-compatible API. The weights are standard mlx-lm
compatible safetensors and should also load in mlx-lm and other MLX apps (untested).
Note: an unrelated oMLX engine bug on 0.7.0.dev1/dev2 can silently drop tool
calls to unregistered function names on the streaming path
(jundot/omlx#3660, open as of
2026-09; 0.6.4 unaffected). It does not affect the weights.
Benchmarks
Practical local tests, limited by compute time, not a standardized academic
suite, performed on oMLX 0.7.0.dev2.
Thinking OFF
| Benchmark | Samples | oQ5e [this repo] | oQ6e [this repo] | oQ4e ¹ | oQ5e ² |
|---|---|---|---|---|---|
| MMLU | 2000 | 88.0% | 88.2% | 87.2% | 88.1% |
| MMLU-Pro | 1000 | 70.4% | 73.4% | 64.4% | 69.2% |
¹ jedisct1/Qwen3.8-Flash-Next-Uncensored-oQ4e-100K-MTP (abliterated lineage)
² GBP-DE/Qwen3.8-Flash-Next-oQ5e-mtp (base, non-abliterated)
At 2000 samples MMLU is flat across all four builds (~88%), within sampling
noise: the abliterated quants are at parity with the base build on broad
knowledge. On MMLU-Pro, accuracy rises with bit width across the
oQ4e/oQ5e/oQ6e series.
Smaller (n=100) GSM8K and HumanEval runs were near ceiling (90-98%) for every
build and are omitted as non-discriminating.
Model architecture
Quantized from Qwen3.8-Flash-Next (sparse Mixture-of-Experts): ~125B LM
parameters, ~6B activated, ~51B N-gram embedding parameters, ~4B MTP
parameters, 48 layers, 512 experts, 10 routed + 1 shared activated. See the
official Qwen model card for full architecture and context details.
Credits
- Base (abliterated) model:
orcarouter/Qwen3.8-Flash-Next-Uncensored,
itself an abliteration ofQwen/Qwen3.8-Flash-Next. - Quantization: oMLX 0.6.4, oQ5e enhanced/imatrix.
- Sensitivity model:
jedisct1/Qwen3.8-Flash-Next-Uncensored-oQ4e-100K-MTP.
License
Qwen Community License 1.0, inherited from the source repository and included asLICENSE. Note the source card labels itself Apache-2.0, which does not match
the license file it ships; review before use or redistribution.