fetch: kingjones Q8_0_ROCMFPX_AGENT payload, frank-small Q5_K_M GGUF

The SGLang INT8 fetch recipe moves to old/ with its route; scripts/ download-frank-small.sh now carries the GGUF quant the endpoint serves.
2026-10-01 23:50:52 -07:00
parent a7c68db9d0
commit 4bb10cd20e
2 changed files with 170 additions and 0 deletions
@@ -0,0 +1,91 @@
+#!/usr/bin/env bash
+# Download kingjones777/Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUF for frank-large
+# (Dankclaw iGPU). Public repo — no auth header, and never a token on the
+# command line (it is world-readable in /proc/<pid>/cmdline).
+#
+# The payload is the repo's highest-quality target plus its MTP draft head and
+# vision projector:
+#   * Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf — ftype 115, 187 tensors at plain
+#     Q8_0 and 311 at GGML_TYPE_Q8_0_ROCMFPX (103). The AGENT routing keeps the
+#     output-head tensors at full Q8_0 (187 vs 2 in the non-AGENT build), which
+#     is the variant to take when serving with the MTP head.
+#   * mtp-Qwen3.8-27B-Q4_0.gguf — the draft head. Q4_0, NOT Q8_0: the head's
+#     per-step cost is its projection over a 248K vocabulary, so the cheaper
+#     head is faster end to end at equal acceptance (author: +6.0% at n-max 1,
+#     +10.2% at n-max 2).
+#   * mmproj-Qwen3.8-27B-BF16.gguf — the vision tower (verified 4/4 on spatial
+#     ground truth with -fa on).
+#
+# Fresh downloads, no resume (`curl -C -` once produced an oversized file on a
+# 31 GiB payload); -f/--fail-with-body so an HTTP 401 is not a success, then
+# byte count and the Hub LFS sha256. Idempotent: complete files are skipped.
+#
+# The repo's own SHA256SUMS covers only the ROCmFP4 files, so the hashes below
+# come from the Hub LFS oids (api/models/<repo>/tree/main).
+#
+# Usage:
+#   scripts/download-frank-large-kingjones.sh [DEST_DIR] [--verify-only]
+set -euo pipefail
+
+REPO="kingjones777/Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUF"
+BASE="https://huggingface.co/${REPO}/resolve/main"
+
+DEST=""
+VERIFY_ONLY=0
+for arg in "$@"; do
+    case "$arg" in
+        --verify-only) VERIFY_ONLY=1 ;;
+        *) DEST="$arg" ;;
+    esac
+done
+DEST="${DEST:-/home/dank/models/kingjones-Qwen3.8-27B-ROCmFP4-STRIX-MTP}"
+
+# name bytes sha256
+FILES=(
+  "Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf 28214425952 f3ef2bdbf56e244fff14b72114dc2aa300b84a4cb4eaf54f2e5e4da1cfcae10b"
+  "mtp-Qwen3.8-27B-Q4_0.gguf 1680271648 051a1764cff8c4f3ee6ae8b00593a0364c7539c67fa50ffc58f3f96509fca38e"
+  "mmproj-Qwen3.8-27B-BF16.gguf 931145888 de2a49866988ea272c43dc2a43ee2662c25725a717ca5b9059ea420a97f53fe8"
+)
+
+mkdir -p "$DEST"
+status=0
+for entry in "${FILES[@]}"; do
+  read -r name size sha <<<"$entry"
+  f="$DEST/$name"
+  have=0
+  if [[ -f "$f" ]] && [[ "$(stat -c%s "$f")" == "$size" ]]; then
+    if sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+      have=1
+    fi
+  fi
+  if (( have )); then
+    echo "OK        $name"
+    continue
+  fi
+  if (( VERIFY_ONLY )); then
+    echo "MISSING   $name"
+    status=1
+    continue
+  fi
+  echo "FETCHING  $name"
+  tmp="$f.part"
+  curl -fsSL --fail-with-body -o "$tmp" "$BASE/$name"
+  mv "$tmp" "$f"
+  if [[ "$(stat -c%s "$f")" != "$size" ]]; then
+    echo "SIZE FAIL $name ($(stat -c%s "$f") != $size)"
+    status=1
+    continue
+  fi
+  if ! sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+    echo "SHA FAIL  $name"
+    status=1
+    continue
+  fi
+  echo "VERIFIED  $name"
+done
+if (( status == 0 )); then
+  echo "DOWNLOAD_DONE $DEST"
+else
+  echo "DOWNLOAD_FAILED $DEST" >&2
+fi
+exit "$status"
@@ -0,0 +1,79 @@
+#!/usr/bin/env bash
+# Download bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M for frank-small
+# (llama.cpp on the RTX 3090). Public repo — no auth header, and never a token
+# on the command line (it is world-readable in /proc/<pid>/cmdline).
+#
+# Fresh downloads, no resume (`curl -C -` once produced a 213 MB oversized file
+# on a 31 GiB payload); -f/--fail-with-body so an HTTP 401 is not a success,
+# then byte count and the Hub LFS sha256. Idempotent: complete files are
+# skipped.
+#
+# The Q6_K file this endpoint served until 2026-10-01 night stays on disk as
+# the rollback target (7793710624 B, LFS oid
+# ef96d05a2ddf2cbb450d1af1ac3860ec769d3575bafa70692ee5609bda3fad7d) — re-fetch
+# it from the same repo with the same recipe if it is ever needed again.
+#
+# Usage:
+#   scripts/download-frank-small.sh [DEST_DIR] [--verify-only]
+set -euo pipefail
+
+REPO="bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF"
+BASE="https://huggingface.co/${REPO}/resolve/main"
+
+DEST=""
+VERIFY_ONLY=0
+for arg in "$@"; do
+    case "$arg" in
+        --verify-only) VERIFY_ONLY=1 ;;
+        *) DEST="$arg" ;;
+    esac
+done
+DEST="${DEST:-/home/dank/models/MiMo-Q5KM}"
+
+# name bytes sha256
+FILES=(
+  "MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf 6876124704 04cf46f2b5584ef922697d6c063f94879434fb86c467f1a09e52daf0cddaf35f"
+)
+
+mkdir -p "$DEST"
+status=0
+for entry in "${FILES[@]}"; do
+  read -r name size sha <<<"$entry"
+  f="$DEST/$name"
+  have=0
+  if [[ -f "$f" ]] && [[ "$(stat -c%s "$f")" == "$size" ]]; then
+    if sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+      have=1
+    fi
+  fi
+  if (( have )); then
+    echo "OK        $name"
+    continue
+  fi
+  if (( VERIFY_ONLY )); then
+    echo "MISSING   $name"
+    status=1
+    continue
+  fi
+  echo "FETCHING  $name"
+  tmp="$f.part"
+  curl -fsSL --fail-with-body -o "$tmp" "$BASE/$name"
+  mv "$tmp" "$f"
+  if [[ "$(stat -c%s "$f")" != "$size" ]]; then
+    echo "SIZE FAIL $name ($(stat -c%s "$f") != $size)"
+    status=1
+    continue
+  fi
+  if ! sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+    echo "SHA FAIL  $name"
+    status=1
+    continue
+  fi
+  echo "VERIFIED  $name"
+done
+if (( status == 0 )); then
+  echo "DOWNLOAD_DONE $DEST"
+else
+  echo "DOWNLOAD_FAILED $DEST" >&2
+fi
+exit "$status"