CoolFace
Modelpublic

OpensourceWTF/Qwen3.8-Flash-Next-MTPLX-oQ4-MTP

sourceHugging Faceapache-2.0updated 28d agoView on Hugging Face
0likes1.1kdownloads
Model Card

Qwen3.8 Flash-Next MLX oQ4 + MTP for MTPLX

This repository republishes the unchanged model artifacts from `Vontra/Qwen3.8-Flash-Next-MLX-oQ4-MTP` at source revision 43a82b3f0ff64fa417fd09ca046580f08d19b0d6, together with MTPLX validation metadata and guarded run receipts.

No tensor was quantized, requantized, or repacked for this upload. Target MoEs and the embedded MTP MoEs remain resident through the normal MLX runner. Only ngram lookups use MTPLX's bounded exact-row SSD cache. The published ngram tensors retain the source-native affine Q4/group-32 storage.

MTPLX runtime

Implementation and review are in `youssofal/MTPLX#368`. The ngram cache has a configurable 10 GiB payload ceiling. Construction measures base residency once and selects the smaller safe payload after reserving KV/MTP, Metal working memory, safety margin, metadata, hash/route tables, alignment, and transient buffers. LRU eviction affects residency only; SSD rows remain authoritative. The server reserves its selected context and the full supported live prefill-chunk range before MLX load. Cache slots use a packed O(1) free chain/linked LRU, and each acquisition submits one bounded I/O task.

Guarded validation

Validated on Apple M5 Max unified memory through the canonical /tmp/mtplx-gpu-exclusive.lock wrapper:

WorkloadResult
Prompt tokens16,384
Generated tokens1,024 exactly
MTP accepted by depth[241, 126, 58]
Prefill396.594 tok/s
Decode27.186 tok/s
Wall time102.297 s
Measured base residency80,435,213,384 bytes
Selected ngram payload1,677,721,600 bytes
Ngram cache overhead892,502,016 bytes
KV/MTP reserve637,046,792 bytes
Projected residency87,937,451,088 bytes
Peak memory85,222,315,432 bytes (79.37 GiB)
Runtime target88,046,829,568 bytes (82 GiB)

The generated completion token hash is 4d876b2e83ed4f4ab63027955b3d7b5494200d837564c7077791927d69e8695f. Raw smoke and 16K/1K receipts are included under receipts/.

Download

bash
mtplx pull OpensourceWTF/Qwen3.8-Flash-Next-MTPLX-oQ4-MTP

mtplx pull finalizes the manifest-backed ngram source files read-only so the retained-descriptor verifier can install the exact SSD row lane. Use the model with the Qwen4 path from MTPLX PR #368. Real MLX execution on the validation host was performed only through the canonical exclusive GPU guard.

Provenance

  • —Source repository: Vontra/Qwen3.8-Flash-Next-MLX-oQ4-MTP
  • —Source revision: 43a82b3f0ff64fa417fd09ca046580f08d19b0d6
  • —MTPLX receipt commit: 446c95f651663c390097bf05e09c7a66045756df
  • —Safetensor shards: 22
  • —Artifact bytes measured locally: 113,324,747,928
  • —Source files matching the pinned revision by size and Hub blob identity: 33
  • —Destination-only MTPLX manifest/validation/receipt files: 7

All 22 safetensor shards and the remaining source model/config files match the pinned source revision. The only source-named metadata differences are this MTPLX model card and Hub-generated .gitattributes.

See MTPLX_VALIDATION.json for machine-readable provenance and metrics.