EigenLabs/Qwen3.8-27B-MTP-4bit

This is a non-standalone, one-layer native MTP proposal head for the pinned target backbone EigenLabs/Qwen3.8-27B-4bit@301e9e2767fd0efcfab7883004720ba3c9a552a1. It proposes tokens only. The target backbone remains authoritative for language tensors, embeddings, the LM head, token acceptance, and final output.

The official model lineage is Qwen/Qwen3.8-27B@1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0. This artifact was derived locally from the exact EigenLabs BF16 MTP artifact EigenLabs/Qwen3.8-27B-MTP-bf16@26a328e070875b0314d652a039b6b59902690f03, never by copying a third-party quantized checkpoint.

Artifact contract

  • model_type: qwen3_5_mtp
  • MTP layers: 1 (layers.0 only)
  • block_size: 3
  • 31 tensor keys, all bare (no mtp. prefix)
  • Eight 2-D matrices stored as canonical .weight, .scales, and .biases tensors
  • Seven 1-D normalization tensors retained in BF16
  • No tokenizer, target embeddings, target LM head, target-backbone weights, or vision weights

This repository must be paired with the immutable target revision above. Updating or downloading this repository alone does not register it in a runtime catalog or enable speculative decoding.

Quantization

Quantization used MLX 0.31.2 directly:

weight, scales, biases = mlx.core.quantize(
    source_bfloat16, group_size=64, bits=4, mode="affine"
)

The packed weights are uint32; affine scales and biases remain BF16. MLX-LM 0.31.3, safetensors 0.7.0, and huggingface-hub 1.7.2 were installed in the conversion environment. Each matrix was independently dequantized with mlx.core.dequantize(..., group_size=64, bits=4, mode="affine", dtype=mlx.float32) and compared with its exact BF16 source.

Matrix Source shape Packed shape Scale/bias shape Max abs error Mean abs error
fc.weight 5120×10240 5120×1280 5120×160 0.041015625 0.0008614016
layers.0.mlp.down_proj.weight 5120×17408 5120×2176 5120×272 0.0546875 0.0010076930
layers.0.mlp.gate_proj.weight 17408×5120 17408×640 17408×80 0.017578125 0.0009606532
layers.0.mlp.up_proj.weight 17408×5120 17408×640 17408×80 0.0341796875 0.0010548841
layers.0.self_attn.k_proj.weight 1024×5120 1024×640 1024×80 0.0166015625 0.0012780037
layers.0.self_attn.o_proj.weight 5120×6144 5120×768 5120×96 0.09765625 0.0016031306
layers.0.self_attn.q_proj.weight 12288×5120 12288×640 12288×80 0.02734375 0.0011431416
layers.0.self_attn.v_proj.weight 1024×5120 1024×640 1024×80 0.021484375 0.0023364164

All source, packed, scale, bias, and dequantized values passed finite-value checks. After the local derivation was complete, all 31 local tensor payloads were compared with the independent pinned reference mlx-community/Qwen3.8-27B-MTP-4bit@b643c01b6d3b094e325edb6ebd832e16c486c575; names, dtypes, shapes, and raw tensor bytes matched exactly.

These checks establish artifact structure and quantization fidelity only. They are not end-to-end generation, acceptance-rate, quality, or speedup claims.

Downloads last month
-
Safetensors
Model size
66.4M params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for EigenLabs/Qwen3.8-27B-MTP-4bit

Base model

Qwen/Qwen3.8-27B
Quantized
(859)
this model