Restore Q6 AGENT large model

This commit is contained in:
Frank
2026-08-25 13:36:07 -07:00
parent 205b11aae4
commit 86d5f38142
8 changed files with 51 additions and 57 deletions
+5 -5
View File
@@ -1,4 +1,4 @@
# Tunables for frank-default-large (kingjones Qwen3.8-27B ROCmFPX Q8 AGENT,
# Tunables for frank-default-large (kingjones Qwen3.8 Uncensored Q6 AGENT,
# dankclaw, Strix Halo gfx1151).
#
# Runtime: ROCmFPX llama.cpp with TurboQuant support. Serves the kingjones
@@ -10,11 +10,11 @@
# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
# ROCmFPX build with TurboQuant KV-cache support.
LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server
LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server
# Model files from https://huggingface.co/kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF.
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT
MODEL_FILE=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf
# Model files from https://huggingface.co/kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF.
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP
MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf
MTP_DRAFT_FILE=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf
MMPROJ_FILE=mmproj-Qwen3.8-27B-BF16.gguf
+4 -4
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env bash
# Serve the kingjones Qwen3.8-27B ROCmFPX Q8 AGENT model as frank-default-large.
# Serve the kingjones Qwen3.8 Uncensored Q6 AGENT model as frank-default-large.
# The deployment uses a standalone MTP draft head and Turbo4 V-side KV cache.
set -euo pipefail
@@ -12,9 +12,9 @@ if [[ -f "$ENV_FILE" ]]; then
set +a
fi
: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT}"
: "${MODEL_FILE:=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf}"
: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
: "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}"
: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-BF16.gguf}"
: "${ALIAS:=frank-default-large}"