record(QUANT-GGUF-IQ-TENSTORRENT): tracker + per-encoding waves for the APEX-I-Nano IQ family - #3177
Merged
Merged
Conversation
…he APEX-I-Nano IQ family
Ettore's mudler/Qwen3.8-27B-APEX-I-Nano.gguf (10.7 GB) packs the 27B into
the P150's 32 GiB with real headroom, but its tensor census is IQ-dominant
(164 IQ3_XXS + 89 IQ2_S + 44 IQ2_XXS + 78 Q3_K of 2,598 tensors) and the
TENSTORRENT keep-quant registered set is exactly {Q4_K, Q5_K, Q6_K,
Q8_0} — the artifact refuses by name on the P150 today.
This lands the records: the QUANT-GGUF-IQ-TENSTORRENT row (INVENTORIED,
census as evidence) in the quantization matrix, the tracker issue with
the census and the ordering (the Q4_K_M 27B verdict in flight takes the
device first), and four per-encoding device-wave issues on the existing
encoding rows (IQ3_XXS READY, IQ2_XXS ACTIVE, IQ2_S INVENTORIED — its
CPU vec_dot is a prerequisite, Q3_K PARTIAL). ssm_out-style caveats: no
code, no promises — each wave specs red-first on its own row.
Records-only: the census is the newly filed gap; the decode chains are
the waves the issues scope.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:zai/glm-5.3-flash [maki]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
record(QUANT-GGUF-IQ-TENSTORRENT): tracker + per-encoding waves for the APEX-I-Nano IQ family
Ettore's mudler/Qwen3.8-27B-APEX-I-Nano.gguf (10.7 GB) packs the 27B into
the P150's 32 GiB with real headroom, but its tensor census is IQ-dominant
(164 IQ3_XXS + 89 IQ2_S + 44 IQ2_XXS + 78 Q3_K of 2,598 tensors) and the
TENSTORRENT keep-quant registered set is exactly {Q4_K, Q5_K, Q6_K,
Q8_0} — the artifact refuses by name on the P150 today.
This lands the records: the QUANT-GGUF-IQ-TENSTORRENT row (INVENTORIED,
census as evidence) in the quantization matrix, the tracker issue with
the census and the ordering (the Q4_K_M 27B verdict in flight takes the
device first), and four per-encoding device-wave issues on the existing
encoding rows (IQ3_XXS READY, IQ2_XXS ACTIVE, IQ2_S INVENTORIED — its
CPU vec_dot is a prerequisite, Q3_K PARTIAL). ssm_out-style caveats: no
code, no promises — each wave specs red-first on its own row.
Records-only: the census is the newly filed gap; the decode chains are
the waves the issues scope.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:zai/glm-5.3-flash [maki]