Views
No views yet
| Total | ~30B (Qwen3-Coder-30B-A3B) |
| Active / token | ~3B |
| Context | upstream card |
| Arch | MoE · Qwen3-Coder-30B-A3B |
| Default OS path | Community GGUF/MLX candidates only (weights not in this repo) |
| Source | Qwen/Qwen3-Coder-30B-A3B-Instruct |
| This pack | runtime scaffold only — no weights · parked · unmeasured |
HF native Parameters badge stays empty (no checkpoint in this repo) — size is the table above. Native Model tree is enabled via YAMLbase_model: Qwen/Qwen3-Coder-30B-A3B-Instructfor findability only — this is not a finetune/adapter/quant of that checkpoint.
| Status | Parked scaffold |
| Measured smoke | None |
| diy_gguf | false |
| Host class | Apple Silicon Mac (future measure) |
| public_promo_before_launch | false |
| License | Apache-2.0 · full text in LICENSE |
| Base | Qwen3-Coder-30B-A3B-Instruct (not Qwen3-Coder-Next) |
1Qwen/Qwen3-Coder-30B-A3B-Instruct ← base (official)
2├── community GGUF / MLX peers ← planning candidates only (unmeasured)
3└── hizrianraz/Qwen3-Coder-30B-A3B-Mac-Agentic ← this pack (runtime scaffold · parked · unmeasured)base_model so Hub does not attach base_model:finetune / quantized tree relation. Upstream cited in prose + links only.
This pack is not a checkpoint. No library_name: gguf. No base_model_relation: quantized.| Field | Value | Source |
|---|---|---|
| Architecture | MoE · Qwen3-Coder-30B-A3B | Qwen/Qwen3-Coder-30B-A3B-Instruct |
| Total parameters | ~30B | upstream card |
| Activated / token | ~3B | upstream card (A3B) |
| Not to confuse with | Qwen3-Coder-Next (~80B-A3B) | different base |
| Pack role | Mac runtime scaffold only · parked · unmeasured | this repo |
| Pack | Role |
|---|---|
| Laguna-S-2.1-Spark-Agentic | Sole measured Aug 3 flagship |
| Qwen3-Coder-Next-Spark-Agentic | Preview / unverified Spark probe |
| This pack | Parked Mac candidate |