Qwen3.8 27B

Q8_0 · bartowski / OrcaRouter · Preserved candidate · quality ungraded

bartowski's Q8_0 GGUF of OrcaRouter's modified Qwen3.8 27B, preserved as the higher-precision GGUF comparison candidate.

Benchmark results · Files · Download · Runtime · Provenance · Full collection

Join Infinity on Discord

Get model support, request models and quants, discuss benchmarks, and follow new releases and model improvements.

Join the Infinity community

All model tests, per-question scores, experiment history and scoring methods

Qwen effort study — separate full-404 cohort: medium 82.87/100 versus xhigh 84.41/100; paired difference +1.54 points (95% interval [-1.71, +4.82]). 404 collected questions, 403 valid questions graded per effort; one invalid reference annotation excluded symmetrically. The historical 202-question cross-model comparison below is unchanged. Study, timing and blind subjective results.

Preserved and documented by isilicon / Mango. The original model, modification and quantization remain the upstream creators' work. This repository adds attributed preservation and exact-configuration evaluation, with the selected source bytes unchanged.

At a glance

GB is decimal and GiB is binary. Payload size is disk/storage size, not a claim that the model fits in the same amount of VRAM. Runtime, KV cache, working memory and companions add their own requirements.

Mango evaluation

No standalone Mango quality score has been published for these exact files. This candidate is preserved, but its completed matched grade is not part of this card release.

Related configurations measured separately

These results describe the linked configurations, not this artifact. A change of quant, modification lineage, draft, engine or tokenizer can change the result.

A completed score requires a native preflight, matching frozen prompts, 202 suite answers, 12 agent cases, archive verification and the same reference graders. The benchmark methodology describes the protocol; publisher-side results are retained separately below.

Runtime and compatibility

The selected mirror contains the main Q8_0 GGUF. Upstream projector and MTP files outside the selection are not implicitly included. Native load, available context and any speculative path require validation.

Higher precision is a hypothesis to test, not an inherited score or throughput guarantee.

The local evaluation covers text/tool tasks. It does not establish the full advertised context ceiling, image/audio quality or every optional speculative-decoding path. Publisher capabilities and Mango-verified behavior are separate scopes.

Companion artifacts

No separate companion mirror is declared in this selected manifest. This does not imply that every optional upstream projector, draft head or multimodal path is included; consult the exact file list.

Files and integrity

Full paths, byte sizes and complete SHA-256/Git blob identities are in SOURCE_MANIFEST.json. Available original README/license/notice files are also preserved. MIRROR_STATUS.json records the earlier source-file verification; MODEL_CARD_STATUS.json records this documentation refresh separately.

Download and use

The commands pin the already-verified mirror weight revision. Documentation can advance on main without changing that preserved weight snapshot. Keep original subfolders and all shards.

python -m pip install -U huggingface_hub

hf download isilicon/mango-qwen27-orca-q8 \
  orcarouter_Qwen3.8-27B-Uncensored-Q8_0.gguf \
  --revision 54dcc31e6c150e1a48581e161a0bef1c36fdf1f5 \
  --local-dir ./weights/qwen27-orca-q8

Load example and setup scope

llama-server \
  --model ./weights/qwen27-orca-q8/orcarouter_Qwen3.8-27B-Uncensored-Q8_0.gguf \
  --host 127.0.0.1 --port 8080 --ctx-size 32768 \
  --jinja --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0

This is a load-command pattern, not a validated Mango inference or performance result for this candidate. Check architecture support before loading; enable projector/MTP options only after their own preflight.

Provenance and license

The publisher documents llama.cpp b10630 quantization and the OrcaRouter source checkpoint. It is a different representation and runtime path from the graded MLX4 + TensorFold/DFlash2 configuration.

Original notices, base-model conditions and the publisher's stated limitations still apply. Downloadable preservation does not add new license rights. Source-described refusal modification and publisher-side benchmark claims have not been independently re-measured by this Mango task cohort.

Original publisher documentation

The unchanged upstream README and pinned source card retain the original usage guidance, technical discussion, attribution, caveats and citations.

Read the complete original publisher card

Source reference. The following is the original publisher's documentation. Its other quants, full-model files, context claims and benchmark tables can exceed the selection in this mirror. Relative asset/file URLs are qualified to the pinned original source; publisher measurements remain separate from Mango measurements.

Llamacpp imatrix Quantizations of Qwen3.8-27B-Uncensored by orcarouter

Using llama.cpp release b10630 for quantization.

Original model: https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored

Model details:

• Parameter count: 28B
• Input support: text, image (with mmproj file) - details
• Speculative decoding: yes (MTP) - details
• imatrix: yes - details

How to run

Prompt format

<|im_start|>system
Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.

{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>

Don't know which to choose? Grab Q4_K_M (17.77GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Download a specific file:

hf download bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF --include "orcarouter_Qwen3.8-27B-Uncensored-Q4_K_M.gguf" --local-dir ./

Downloading using the Hugging Face CLI

Click to view download instructions

First, make sure you have the Hugging Face CLI installed:

pip install -U "huggingface_hub[cli]"

Download a specific file:

hf download bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF --include "orcarouter_Qwen3.8-27B-Uncensored-Q4_K_M.gguf" --local-dir ./

The files marked true in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run:

hf download bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF --include "orcarouter_Qwen3.8-27B-Uncensored-bf16/*" --local-dir ./

You can either specify a new local-dir (orcarouter_Qwen3.8-27B-Uncensored-bf16) or download them all in place (./)

How to run

These quants run with llama.cpp - installable in one line via llama.app:

curl -LsSf https://llama.app/install.sh | sh
llama-server -hf bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF:Q4_K_M

llama-server includes a built-in chat web UI, served at http://localhost:8080 by default.

These quants were made with llama.cpp release b10630 - if this model's architecture is newly supported, you'll need that release or newer to run them.

They also work in: LM Studio · koboldcpp · ramalama · Jan AI · Text Generation Web UI · LoLLMs · Atomic Chat

Multimodal

This model supports image input. Alongside the quants, this repo includes the multimodal projector files mmproj-orcarouter_Qwen3.8-27B-Uncensored-f16.gguf and mmproj-orcarouter_Qwen3.8-27B-Uncensored-bf16.gguf, which pair with any quant above.

llama.cpp downloads the mmproj automatically when using -hf as shown above; if you're loading files manually, pass it with --mmproj.

MTP

This model has MTP (Multi-Token Prediction) layers, and they are included in these quants

MTP layers act as a built-in draft model, letting llama.cpp run speculative decoding for faster generation. To use them, add the following flag to your llama.cpp command:

--spec-type draft-mtp

Note: the MTP layers are stored at Q4_0 in the imatrix quants (except for the Q8_0 quant), since imatrix calibration does not exercise them. Q4_0 is chosen for its speed which massively benefits MTP performance.

imatrix

All quants made using imatrix option, with a calibration corpus rendered through this model's own chat template. The corpus pairs plain prose with tool-calling and reasoning conversations (corpus source data), encoded exactly as this model sees them at inference and processed with --parse-special, so chat-format special tokens contribute to the importance matrix. The corpus rendered for this model is included in this repo: orcarouter_Qwen3.8-27B-Uncensored-calibration-v6.txt. The imatrix is available here: orcarouter_Qwen3.8-27B-Uncensored-imatrix.gguf.

Calibration render details

{
  "generator": "auto_quant_v2 calibration renderer",
  "recipe": "calibration-v6",
  "model": "Qwen3.8-27B-Uncensored",
  "encoder": "chat_template",
  "chunk_size": 512,
  "prose_chunks": 214,
  "tool_chunks": 369,
  "total_chunks": 583,
  "tool_chunk_fraction": 0.633,
  "n_conversations": 137,
  "extension_convs_used": 0,
  "conversation_token_lengths": [
    604,
    1667,
    1297,
    1559,
    1185,
    1404,
    3220,
    866,
    1267,
    1462,
    1107,
    2136,
    921,
    1293,
    2829,
    1313,
    1160,
    1026,
    777,
    758,
    1402,
    1098,
    1447,
    1242,
    1912,
    1538,
    1694,
    948,
    1455,
    1686,
    1609,
    1260,
    1308,
    1077,
    1060,
    1752,
    1691,
    1215,
    517,
    1950,
    1451,
    1166,
    1438,
    2042,
    2130,
    1355,
    1649,
    947,
    2996,
    1142,
    2908,
    827,
    1064,
    1010,
    947,
    738,
    2530,
    955,
    1188,
    1127,
    1271,
    1211,
    966,
    1259,
    1223,
    1628,
    953,
    1592,
    2166,
    881,
    365,
    1162,
    3375,
    2876,
    749,
    982,
    1072,
    1113,
    1338,
    1122,
    1191,
    835,
    1250,
    1111,
    1331,
    1586,
    1443,
    2106,
    913,
    698,
    2806,
    682,
    1443,
    1715,
    1987,
    1243,
    683,
    1396,
    1168,
    1769,
    1884,
    1755,
    857,
    1055,
    1077,
    2896,
    780,
    774,
    803,
    1452,
    1092,
    1617,
    808,
    392,
    361,
    2666,
    1058,
    1179,
    1870,
    2079,
    2735,
    2717,
    856,
    1020,
    880,
    999,
    1279,
    1039,
    882,
    1397,
    870,
    750,
    1783,
    1067,
    957,
    1356,
    1519
  ],
  "warnings": []
}

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

llama.cpp automatically "repacks" weights into an interleaved layout at load time for faster inference on ARM and AVX machines - details in this PR. This once required downloading special Q4_0_4_4/4_8/8_8 files; those are long gone. Online repacking now covers Q4_0, IQ4_NL, and most K-quants, so no special quant choice is needed for CPU inference.

Which file should I choose?

Click here for details

An older (early 2024) but still useful write-up with charts comparing quant performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Hugging Face can also do this math for you: add your hardware in your Local Apps settings and the model page will show which files fit.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Preservation record

Selected source bytes are verified against pinned metadata; the original eight graded mirrors also passed the previously recorded anonymous 1 MiB weight-prefix checks. This is not a full independent-device restore/load test. Hugging Face repository copies share a provider and do not guarantee permanent storage.

Collection · Source manifest · Original documentation