From 751180fdc18b1737f18296cd49a229887580a291 Mon Sep 17 00:00:00 2001 From: Felipe Cardoso Date: Sun, 26 Apr 2026 20:06:18 +0200 Subject: [PATCH] feat(serve): upgrade daily driver to qwen3.6-35b-a3b q6_k_xl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Switch `make serve` default to Qwen3.6 UD Q6_K_XL (32 GB, hybrid DeltaNet, near-lossless) and register it in the model catalog. Add --jinja to the llama-server launcher so tool/function calling works — without it clients silently ignore tool definitions advertised by the server. --- Makefile | 4 ++-- configs/models.conf | 1 + scripts/serve/launch.sh | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 6b0521c..1008f34 100644 --- a/Makefile +++ b/Makefile @@ -39,8 +39,8 @@ benchmark-compare: ## Compare two benchmark runs (usage: make benchmark-compare @bash bin/benchmark compare $(BEFORE) $(AFTER) # --- Serve --- -serve: ## Launch APEX I-Compact daily driver (2 slots, 256K ctx) - @bash bin/serve -m Qwen3.5-35B-A3B-Claude-Distilled-APEX-I-Compact.gguf --parallel 2 --ctx 262144 $(ARGS) +serve: ## Launch Qwen3.6-35B-A3B UD-Q6_K_XL daily driver (2 slots, 256K ctx) + @bash bin/serve -m Qwen3.6-35B-A3B-UD-Q6_K_XL.gguf --parallel 2 --ctx 262144 $(ARGS) serve-custom: ## Launch llama-server with custom model (ARGS="-m MODEL.gguf") @bash bin/serve $(ARGS) diff --git a/configs/models.conf b/configs/models.conf index 2eb0fdc..44e2aa4 100644 --- a/configs/models.conf +++ b/configs/models.conf @@ -27,6 +27,7 @@ qwen3.5-27b-opus-distill|Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distille qwen3.5-35b-a3b-q4|unsloth/Qwen3.5-35B-A3B-GGUF|Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf|21|moe|MoE 35B, 3B active, Unsloth dynamic XL qwen3.5-35b-a3b-q8|unsloth/Qwen3.5-35B-A3B-GGUF|Qwen3.5-35B-A3B-Q8_0.gguf|37|moe|MoE 35B Q8, near-full precision qwen3.5-35b-a3b-apex-compact|mudler/Qwen3.5-35B-A3B-Claude-Distilled-APEX-GGUF|Qwen3.5-35B-A3B-Claude-Distilled-APEX-I-Compact.gguf|17|moe|MoE 35B Claude-distilled APEX, I-Compact quant +qwen3.6-35b-a3b-q6xl|unsloth/Qwen3.6-35B-A3B-GGUF|Qwen3.6-35B-A3B-UD-Q6_K_XL.gguf|32|moe|Qwen3.6 MoE 35B/3B active, UD Q6 XL (near-lossless, hybrid DeltaNet) nemotron-cascade2-q8|bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF|nvidia_Nemotron-Cascade-2-30B-A3B-Q8_0.gguf|31|moe|Nemotron Cascade 2, Mamba-2 hybrid (replaces Nano) # ── Coding models ───────────────────────────────────────── diff --git a/scripts/serve/launch.sh b/scripts/serve/launch.sh index 27894bf..1638c98 100755 --- a/scripts/serve/launch.sh +++ b/scripts/serve/launch.sh @@ -106,6 +106,7 @@ SERVER_ARGS=( -ngl 99 # Full GPU offload --no-mmap # Direct load, no mmap overhead -fa on # Flash attention + --jinja # Required for tool calling (clients ignored without it) -m "$TOOLBOX_MODEL_PATH" -c "$CTX_SIZE" # Context size --cache-type-k q4_0 # KV cache quantization (fastest on Vulkan)