Model architecture: Thinking Machines Lab Inkling-Small
- Parameters: 276B total / 12B active
- Input: Text, image, audio
- Output: Text
Validated inference engine: vLLM
Model optimizer: AMD Quark (0.12.post1+rocm72.torch2.11)
- Quantized layers: MoE routed experts in transformer layers 3 through 41
- Weight quantization: OCP MXFP4, static, group size 32, E8M0 scales
- Activation quantization: OCP MXFP4, dynamic, group size 32, E8M0 scales

This checkpoint was built from thinkingmachines/Inkling-Small revision b2d4f225a02032c5d154bff748ab5a00c5ca26e4 by applying AMD Quark OCP MXFP4 quantization to the BF16 routed experts. Routed-expert weights are stored as packed MXFP4 weights with E8M0 scales. Dense layers 0 through 2, attention, shared experts, embeddings, norms, the audio and vision towers, MTP, and other non-routed components remain in their source formats.

Environment

The file-to-file conversion and validation targeted AMD gfx950 and used:

Container: docker.io/rocm/vllm-dev:nightly_main_20260714
Python: 3.12
ROCm/HIP: 7.2
PyTorch: 2.11.0+gitd0c8b1f
AMD Quark: 0.12.post1+rocm72.torch2.11
Expert chunk size: 8

The paired quality evaluation used the same GPU type and TP8 topology, with Transformers 5.14.1 and vLLM commit 846e2d01a0be00acf31f1a354059c7c302c93042 (0.23.1rc1.dev1212+g846e2d01a).

Evaluation

Benchmark	BF16 Reference	MXFP4	MXFP4 − BF16
BFCL exact calls	76.54% (1,034/1,351)	76.76% (1,037/1,351)	+0.22 pp
BFCL all-live macro	76.56%	71.01%	−5.55 pp
MMAU (official string match)	75.5% (755/1,000)	76.3% (763/1,000)	+0.80 pp
GPQA Diamond	89.19% (883/990)	87.98% (871/990)	−1.21 pp
AIME 2026	94.58% (908/960)	94.58% (908/960)	0.00 pp

Refer to the Inkling-Small model card for architecture, training, intended-use, safety, and acceptable-use details.

EmbeddedLLM/Inkling-Small-MXFP4

Inkling-Small-MXFP4

Model Overview

Environment

Evaluation

EmbeddedLLM/
Inkling-Small-MXFP4