GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
brandonmusic
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
brandonmusic
Model Tree
Qwen/Qwen3-30B-A3B-Base
Input Modalities
Output Modalities
Supported Functionality
The allocation has a logical average rate of 3.5 bits per MoE expert-weight element (9,216 K3 and 9,216 K4 matrix choices). This repository stores those reconstructions in BF16 and is therefore about the size of the BF16 base model. It is not a compact 3.5-bpw checkpoint and is not runtime-qualified. The current official BTX format couples gate/up bit rates, while this experiment selects gate and up independently; publishing it as official BTX would misrepresent the measured model.
Against sealed BF16 teacher logits on 2,047 next-token positions from the immutable WikiText-2-raw-v1 test-prefix window:
| Metric | Value |
|---|---|
| Mean KLD | 0.0550610707425 |
| Median KLD | 0.0129405570572 |
| P95 KLD | 0.246331153046 |
| Maximum KLD | 3.09338690461 |
Allocation SHA256: 10bb3b71a2258500b281e3b37d57657e5e0ecf9318bb9c1a3fc6dbd2326e63c4
KLD report seal: f1ac3903116141faa18bf2f8253ebd875730451f8c0a23645b366fd5517a072b
Independent verification seal: b866e70b5e48433b3d9a014531acb0c460b3788198f3f8855830b6e58fd93fe6
The historical and causal arms use the same exact Qwen3-30B-A3B-Base
revision, candidate reconstructions, 9,216 K3 plus 9,216 K4 matrix choices,
sealed BF16 teacher, token IDs, SDPA attention implementation, and four-layer
reanchoring cadence. Only the exact-rate expert-matrix allocation changes.
| Exact-3.5 routed-expert allocation | Mean KLD | Top-1 agreement |
|---|---|---|
| Historical Hessian/router allocation | 0.0624957262898 | 0.90131900342 |
| Aumann–Shapley/Fisher causal allocation | 0.0550610707425 | 0.912066438691 |
The causal allocation lowers KLD by 11.8963%
and gains 1.0747 percentage points in
top-1 agreement. It changes 9,392 of the 18,432
matrix choices without changing the exact logical rate or stored candidate
payload budget. The independent float64 replay differs by at most
9.04e-13 per token.
The broader panel follows ExLlamaV3's published WikiText construction (ten consecutive 2,048-token rows), but both arms and the BF16 teacher are executed with Transformers SDPA. It is therefore a matched internal replication—not a claim that Transformers SDPA and ExLlamaV3-native attention are numerically identical.
| Exact-3.5 routed-expert allocation | Mean KLD | Top-1 agreement |
|---|---|---|
| Historical Hessian/router allocation | 0.049088886473 | 0.908203125 |
| Aumann–Shapley/Fisher causal allocation | 0.0452937027269 | 0.910888671875 |
The causal allocation lowers 20k-panel KLD by
7.7312% and gains
0.2686 percentage points in
top-1 agreement.
Independent float64 replay has maximum per-token differences of
0 for the causal arm and
0 for the historical
arm. The complete teacher/student logits, per-token vectors, reports, manifests,
and verification artifacts are retained in the reproducibility dataset.
The full candidates, calibration/Hessian artifacts, teacher and student logits,
token window, manifests, hashes, and receipts are published in
brandonmusic/shapleymcg-qwen3-30b-a3b-reproducibility.
The executable pipeline and methodology are in
brandonmmusic-max/shapleymcg.
The same full causal allocator was subsequently run on the post-trained
Qwen/Qwen3-30B-A3B parent using its separately fitted, retained MCG candidate
inventory. On a matched 20,480-position eager WikiText panel at exact 3.5
routed-expert BPW, it lowered KLD from the predecessor routed-p2 allocation's
0.0411226321813 to 0.0403685517455 (1.833736%) and raised top-1 agreement
from 0.924267578125 to 0.925683593750. Independent float64 replay had zero
maximum tokenwise difference.
The allocation also transferred to TurboDerp's unchanged exact-3.5 expert
candidate pool, lowering its matched KLD from 0.0302749179770 to
0.0292690766473 (3.322359%) and improving top-1 agreement by
0.273438 percentage points. The separately produced MCG pool measured
0.0457931025429 under the same allocation and body scope. That comparison
does not isolate the codec: calibration corpus and hidden-state policy,
rotation/scaling choices, procedural selection, and numeric encoder
implementation also differ.
The stricter allocator-only test reconstructs both arms from the identical
published TurboDerp K3/K4 candidates at exact 3.5 expert BPW. TurboDerp
v0.0.1's carried-surplus rule measured KLD 0.0339415351804; full
Aumann–Shapley/Fisher measured 0.0292690766473, a 13.766197% reduction,
with a 0.600586 percentage-point top-1 gain and all 10 evaluation rows
favorable. This proves an allocator-only advantage over the v0.0.1 rule on the
common reconstructed candidate bytes; it is not a comparison against a native
TurboDerp 3.5 checkpoint, which was not published for this model.
This model repository remains the Base-parent validation reconstruction; the
post-trained logits and provenance are in
brandonmusic/shapleymcg-qwen3-30b-a3b-posttrained-reproducibility.
The GitHub
complete results ledger
and
method specification
distinguish parent, allocator generation, codec, dense-weight scope, evaluator,
and token panel for every headline number.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
Qwen/Qwen3-30B-A3B-Base.Saturation Makes Quantization Error Additive,
and NVIDIA Model Optimizer PR #2183.