dapack — code pack (graded precision, 10.7 GB)
Qwen3.5-35B-A3B compressed for programming and software work: 10.7 GB instead of 21.2 GB, with every expert still present. The 143 experts this domain routes to are kept at q2_K; the remaining 113 are held at IQ2_XXS (2.06 bpw) under an importance matrix — graded, not deleted, so the pack degrades out of domain instead of breaking.
⚠️ This file requires the dapack runtime
Graded packs carry two expert tensors per layer at different precisions (
ffn_*_exps_cold+dapack.hot_experts_per_layer). Stock llama.cpp / ollama / LM Studio cannot load them. Build the runtime from:https://github.com/R3n3r0/dapack — ready-to-run binaries under Releases (Linux x86_64, ROCm), nothing to compile:
tar xzf dapack-v0.1.0-linux-x86_64-rocm-gfx1151.tar.gz cd dapack-v0.1.0-* && ./dapack serve ~/catalog.dapack # web chat + OpenAI API + routingOn other GPUs, build from the same repo (one command,
scripts/rebuild_fork.sh --applyafter a recursive clone).
Measured capabilities
These numbers are behavioural measurements, not estimates. They ship in the pack's manifest, and the dapack router treats them as hard constraints — a request needing a capability this pack has lost is routed to a pack that has it.
| capability | this pack | full model (21.2 GB) |
|---|---|---|
| code generation | 100% | 100% |
| tool calling (8 probes) | 8/8 | 8/8 |
| Italian (behavioural probe) | 100% | 100% |
| instruction following | 100% | 80% |
| long context (needle @ 3k tokens) | 100% | 100% |
| structured output (JSON) | 100% | 100% |
| translation en→it | 40% ⚠️ | 100% |
What it lost — on purpose, and declared: translation dropped to 40%, because a code calibration spends its precision budget on programming experts. Under the dapack router, translation requests never reach this pack.
Why graded instead of pruned
On the identical expert selection, we measured:
| mechanism | Qwen3.5-35B | Qwen3-30B | tools |
|---|---|---|---|
| surplus experts deleted | 79.0% | 40.0% | 7/8 |
| surplus experts at 2 bits | 82.0% | 93.3% | 8/8 |
On the second architecture deletion loses 53 points and grading loses none. (35B columns measured on this pack's language-domain twin; same base, same recipe.)
Deletion costs ~1 point of reasoning per 1% of experts chosen wrongly and is unrecoverable. A 2-bit expert is present and merely imprecise. Compute cost is unchanged: the top-k budget is partitioned across the two banks, so exactly 8 experts run per token.
Files
| file | size | needs |
|---|---|---|
graded_code.gguf | 10.7 GB | dapack fork |
manifest-fragment.json | — | capability manifest for the catalogue |
Full documentation, tools to build your own domain packs, and every measurement behind this card: https://github.com/R3n3r0/dapack