diff --git a/scripts/deploy-remote.sh b/scripts/deploy-remote.sh
index 2c5418f..86ff4a5 100755
--- a/scripts/deploy-remote.sh
+++ b/scripts/deploy-remote.sh
@@ -1114,6 +1114,7 @@ deploy_llm_small() {
 LLM_MEDIUM_BIN="${LLM_MEDIUM_BIN:-/home/dank/GitPackages/llama.cpp-dflash2/build-rdna4-rocm714/bin/llama-server}"
 LLM_MEDIUM_MODEL="${LLM_MEDIUM_MODEL:-/home/dank/models/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf}"
 LLM_MEDIUM_DRAFT="${LLM_MEDIUM_DRAFT:-/home/dank/models/Qwen3.8-27B-DFlash2-GGUF/Qwen3.8-27B-DFlash2-Q8_0.gguf}"
+LLM_MEDIUM_MMPROJ="${LLM_MEDIUM_MMPROJ:-/home/dank/models/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF/mmproj-BF16.gguf}"
 
 # The three vLLM user units are retired HERE, not left to rot: the proxy
 # published 7770 on the host network, so the llama-server below cannot bind
@@ -1153,6 +1154,11 @@ deploy_llm_medium() {
         echo "frank-medium: fetch it: bash scripts/download-frank-medium-gguf.sh" >&2
         missing=1
     fi
+    if [[ ! -f "$LLM_MEDIUM_MMPROJ" ]]; then
+        echo "ERROR: vision projector absent at $LLM_MEDIUM_MMPROJ" >&2
+        echo "frank-medium: fetch it: bash scripts/download-frank-medium-gguf.sh" >&2
+        missing=1
+    fi
     [[ "$missing" -eq 0 ]] || return 1
 
     retire_vllm_medium_quadlets
diff --git a/scripts/download-frank-medium-gguf.sh b/scripts/download-frank-medium-gguf.sh
index 90934a3..d599922 100755
--- a/scripts/download-frank-medium-gguf.sh
+++ b/scripts/download-frank-medium-gguf.sh
@@ -1,6 +1,5 @@
 #!/usr/bin/env bash
-# Download the frank-medium payload for Dankserver (2x Radeon AI PRO R9700):
-# the target GGUF and the DFlash2 draft model, into /home/dank/models.
+# the target GGUF, the BF16 vision projector and the DFlash2 draft model.
 #
 #   bash scripts/download-frank-medium-gguf.sh
 #   bash scripts/download-frank-medium-gguf.sh --verify-only
@@ -27,6 +26,10 @@ MODEL_REPO="ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF"
 MODEL_DIR="/home/dank/models/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF"
 MODEL_FILE="Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf"
 MODEL_SIZE=31457990112
+# The BF16 vision projector from the same repo; llama-server autoloads any
+# mmproj*.gguf beside the target, so it must land in MODEL_DIR.
+MM_PROJ_FILE="mmproj-BF16.gguf"
+MM_PROJ_SIZE=931145888
 
 DRAFT_REPO="z-lab/Qwen3.8-27B-DFlash2-GGUF"
 DRAFT_DIR="/home/dank/models/Qwen3.8-27B-DFlash2-GGUF"
@@ -55,6 +58,8 @@ dl() { # dl <repo> <dir> <file>
 if [[ "$mode" == "download" ]]; then
     echo "target: $MODEL_REPO"
     dl "$MODEL_REPO" "$MODEL_DIR" "$MODEL_FILE"
+    echo "projector: $MODEL_REPO"
+    dl "$MODEL_REPO" "$MODEL_DIR" "$MM_PROJ_FILE"
     echo "draft: $DRAFT_REPO"
     dl "$DRAFT_REPO" "$DRAFT_DIR" "$DRAFT_FILE"
 fi
@@ -72,6 +77,7 @@ check() { # check <path> <expected>
     fi
 }
 check "$MODEL_DIR/$MODEL_FILE" "$MODEL_SIZE"
+check "$MODEL_DIR/$MM_PROJ_FILE" "$MM_PROJ_SIZE"
 check "$DRAFT_DIR/$DRAFT_FILE" "$DRAFT_SIZE"
 [[ -z "$token" ]] && echo "note: no token used; the byte counts above are the integrity check"
 [[ "$ok" -eq 1 ]] || exit 1
diff --git a/scripts/frank-medium.env b/scripts/frank-medium.env
index 3e1f4a5..bcc28d5 100644
--- a/scripts/frank-medium.env
+++ b/scripts/frank-medium.env
@@ -35,7 +35,7 @@
 # 29.29 GiB, arch qwen35, Unsloth Dynamic 3.0 (per-tensor types from Unsloth's
 # own quant of the same size, on Unsloth's importance matrix).  Abliteration is
 # orcarouter's single refusal direction projected out of 131 tensors; the vision
-# tower is untouched but unused here (text only, see NO_MMPROJ).  The file also
+# tower loads from mmproj-BF16.gguf (see NO_MMPROJ).  The file also
 # carries the model's MTP head (blk.64.nextn.*), so a file-level switch to
 # --spec-type draft-mtp is available without a second copy in VRAM.
 #
@@ -121,6 +121,11 @@ LLAMA_BIN=/home/dank/GitPackages/llama.cpp-dflash2/build-rdna4-rocm714/bin/llama
 # Payload, fetched with scripts/download-frank-medium-gguf.sh.
 MODEL_DIR=/home/dank/models/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF
 MODEL_FILE=Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf
+# The BF16 vision projector, same repo as the target.  llama-server autoloads
+# any mmproj*.gguf beside the model; the serve script refuses to start without
+# it when vision is enabled, so a missing file is a deploy error, not a
+# text-only server that pretends to be multimodal.
+MM_PROJ_FILE=mmproj-BF16.gguf
 DRAFT_MODEL_DIR=/home/dank/models/Qwen3.8-27B-DFlash2-GGUF
 DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-Q8_0.gguf
 
@@ -136,23 +141,30 @@ HIP_VISIBLE_DEVICES=0,1
 DEVICES=ROCm0,ROCm1
 SPLIT_MODE=layer
 
-# 35:30 -- the measured balance at the deployed batch, and the split that leaves
-# the most room: ROCm1 carries the drafter, its KV and the output layers, so it
-# takes fewer target layers.  See SIZING above for the measurement table; one
-# -ts step is one LAYER, worth ~0.43 GiB (DeltaNet) or ~1.43 GiB (attention), so
-# do not move it without re-measuring.
-TENSOR_SPLIT=35,30
+# 36:29 -- one layer over the 35:30 balance, moved to buy headroom on ROCm1,
+# the card that carries the drafter, its KV, the output layers and the heavier
+# compute buffers, now that the context grew to 327680 (see below).  Fit at
+# the deployed point (36:29, ctx 327680, batch 6144 x ubatch 512, two slots,
+# DFlash2 + ngram-mod, mmproj on ROCm0): ROCm0 29.19 / ROCm1 26.04 GiB of
+# 31.86, i.e. 2.67 / 5.82 GiB free and a 3.15 GiB gap BY CONSTRUCTION -- the
+# balance point at this context is 34:31 (0.11 GiB gap) and the operator chose
+# headroom on the drafter card over balance.  See SIZING above for the
+# measurement table; one -ts step is one LAYER, worth ~0.43 GiB (DeltaNet) or
+# ~1.43 GiB (attention), so do not move it without re-measuring.
+TENSOR_SPLIT=36,29
 
 NGL=999
 # Auto-fit has no business resizing a context we set explicitly.
 FIT=off
 FLASH_ATTN=on
 
-# The model's full window (n_ctx_train 262144) divided over TWO slots, so each
-# conversation gets 131072 -- verified at load as `n_slots = 2, n_ctx_slot =
-# 131072`.  --parallel DIVIDES --ctx-size, so more slots would shrink every
-# conversation rather than grow the cache.
-CTX_SIZE=262144
+# 327680 positions over TWO slots, so each conversation gets 163840 --
+# --parallel DIVIDES --ctx-size, so more slots would shrink every
+# conversation rather than grow the cache.  The checkpoint's trained window is
+# 262144 and the GGUF carries NO rope scaling (freq_base 1e7, no YaRN keys),
+# so positions beyond 262144 extrapolate on the base rope: it runs, and 1.25x
+# is a modest ask of it, but the extra 65k is untrained territory.
+CTX_SIZE=327680
 PARALLEL=2
 
 # MEASURED 2026-09-16 with scripts/bench-batch-ubatch.sh on this box: llama-bench,
@@ -292,6 +304,9 @@ SPEC_NGRAM_N_MATCH=24
 SPEC_NGRAM_N_MIN=48
 SPEC_NGRAM_N_MAX=64
 
-# Text only: the server must not autoload a vision tower.  Vision stays on
-# frank-small (Dankclaw, RTX 3090), which is the fleet's image endpoint.
-NO_MMPROJ=1
+# Vision enabled: llama-server autoloads mmproj-BF16.gguf from MODEL_DIR
+# (888 MiB, lands on ROCm0 -- the fit above charges it there).  frank-small
+# (Dankclaw, RTX 3090) remains the fleet's dedicated image endpoint; this
+# makes frank-medium multimodal too, which is why the seam flips from
+# "text only" to "vision loads with the model".
+NO_MMPROJ=0
diff --git a/scripts/serve-frank-medium.sh b/scripts/serve-frank-medium.sh
index 3afcaff..0b1dbe3 100755
--- a/scripts/serve-frank-medium.sh
+++ b/scripts/serve-frank-medium.sh
@@ -89,7 +89,8 @@ fi
 : "${SPEC_NGRAM_N_MIN:=48}"
 : "${SPEC_NGRAM_N_MAX:=64}"
 
-NO_MMPROJ="${NO_MMPROJ:-1}"
+NO_MMPROJ="${NO_MMPROJ:-0}"
+: "${MM_PROJ_FILE:=mmproj-BF16.gguf}"
 
 export HIP_VISIBLE_DEVICES
 
@@ -106,6 +107,14 @@ if [[ ! -r "$MODEL" ]]; then
     echo "fetch it with: bash $SCRIPT_DIR/download-frank-medium-gguf.sh" >&2
     exit 1
 fi
+if [[ "$NO_MMPROJ" != "1" ]]; then
+    MM_PROJ="$MODEL_DIR/$MM_PROJ_FILE"
+    if [[ ! -r "$MM_PROJ" ]]; then
+        echo "vision is enabled but the projector is missing: $MM_PROJ" >&2
+        echo "fetch it with: bash $SCRIPT_DIR/download-frank-medium-gguf.sh" >&2
+        exit 1
+    fi
+fi
 if [[ -n "$CHAT_TEMPLATE_FILE" && ! -r "$CHAT_TEMPLATE_FILE" ]]; then
     echo "missing or unreadable chat template: $CHAT_TEMPLATE_FILE" >&2
     exit 1
diff --git a/tests/frank_medium_unit.bats b/tests/frank_medium_unit.bats
index b2c9c58..a9e042a 100755
--- a/tests/frank_medium_unit.bats
+++ b/tests/frank_medium_unit.bats
@@ -155,9 +155,12 @@ print('draft-model wiring ok')
     [ "$parallel" -ge 1 ]
     [ "$batch" -ge "$ubatch" ]
     [ "$cache_k" = "f16" ] && [ "$cache_v" = "f16" ]
-    # Per card, calibrated against rocm-smi at the deployed point (35:30, ctx
-    # 262144, batch 6144 x ubatch 512, two slots, DFlash2), where the two cards
-    # measured 6.44 / 6.90 GiB free.  The fit reproduces that to 0.01 GiB.
+    # Per card, calibrated against rocm-smi at the 35:30 / ctx 262144 / batch
+    # 6144 x ubatch 512 / two slots / DFlash2 point, where the two cards
+    # measured 6.44 / 6.90 GiB free.  The fit reproduces card 1 to 0.00 GiB
+    # and card 0 to 0.86 GiB at that point; it is a GATE, not a meter -- the
+    # deployed point is re-measured on the host after every split/ctx/batch
+    # move (the 2026-09-17 move to 36:29 / 327680 / mmproj is the current one).
     #
     #   card 0 = its share of the weights and of the KV (qwen35 spends KV on
     #            its 16 full-attention layers only: 2 (K,V) x 4 heads x 256 dim
@@ -192,11 +195,20 @@ print('draft-model wiring ok')
     # allocation.
     local kv_pos=65536 draft_kv_pos=20480 floor slack
     local card_hi card_lo diff
+    local mmproj=931145888   # mmproj-BF16.gguf, autoloaded onto the primary device
     floor=$(( 1536 * 1024 * 1024 ))     # 1.5 GiB per card
-    slack=$(( 512 * 1024 * 1024 ))      # one DeltaNet layer, rounded up
+    # One DeltaNet layer at the old shape was the finest the balance could be
+    # tuned, so the slack used to be one DeltaNet layer.  The 2026-09-17 move
+    # to 36:29 at ctx 327680 traded balance for headroom on the drafter card
+    # (the balance point at this context is 34:31, gap 0.11 GiB; 36:29's gap
+    # is 3.15 GiB BY CONSTRUCTION, and the operator chose it).  The slack is
+    # that gap, rounded up: tighter rejects the deployed split, looser stops
+    # being a balance check at all.
+    slack=$(( 3225 * 1024 * 1024 ))
     card_hi=$(( MODEL_BYTES * split_hi / (split_hi + split_lo) \
               + kv_pos * ctx * split_hi / (split_hi + split_lo) \
               + 381898377 \
+              + mmproj \
               + 1363 * 1024 * ubatch ))
     card_lo=$(( MODEL_BYTES * split_lo / (split_hi + split_lo) \
               + DRAFT_BYTES \
@@ -208,13 +220,21 @@ print('draft-model wiring ok')
     [ "$card_lo" -le $(( CARD_BYTES - floor )) ]
     diff=$(( card_hi - card_lo )); [ "$diff" -ge 0 ] || diff=$(( -diff ))
     [ "$diff" -le "$slack" ]
-    # ...and the window may not exceed what the checkpoint was trained for.
-    [ "$ctx" -le 262144 ]
+    # ...and the window may not wander far past what the checkpoint was
+    # trained for (262144; the GGUF carries no rope scaling, so the extra 65k
+    # extrapolates on the base rope).
+    [ "$ctx" -le 327680 ]
 }
 
-@test "frank-medium is text only: the vision tower stays on frank-small" {
-    grep -q '^NO_MMPROJ=1$' "$ENV_FILE"
-    grep -q -- '--no-mmproj' "$SERVE"
+@test "vision is enabled: the BF16 projector loads with the model" {
+    grep -q '^NO_MMPROJ=0$' "$ENV_FILE"
+    grep -q '^MM_PROJ_FILE=mmproj-BF16.gguf$' "$ENV_FILE"
+    # The serve script refuses to start without the projector when vision is
+    # on, so a missing file is a deploy error, not a silent text-only server.
+    grep -q 'vision is enabled but the projector is missing' "$SERVE"
+    # And the download script fetches and byte-verifies it.
+    grep -q '^MM_PROJ_SIZE=931145888$' "$FETCH"
+    grep -q -- 'check "$MODEL_DIR/$MM_PROJ_FILE" "$MM_PROJ_SIZE"' "$FETCH"
 }
 
 @test "the fleet endpoint and the predecessor's sampler defaults survive" {