diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index 8a1bff65a..e32dd7a56 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -1481,6 +1481,11 @@ struct vk_op_binary_push_constants {
     float param1; float param2; int32_t param3;
 };
 
+// Distinct type with the same layout so concat can overload tensor offset initialization.
+struct vk_op_concat_push_constants : vk_op_binary_push_constants {};
+static_assert(sizeof(vk_op_concat_push_constants) == sizeof(vk_op_binary_push_constants));
+static_assert(std::is_standard_layout_v<vk_op_concat_push_constants>);
+
 struct vk_op_multi_add_push_constants {
     // shape for dst
     uint32_t ne20; uint32_t ne21; uint32_t ne22; uint32_t ne23;
@@ -2246,6 +2251,40 @@ static uint32_t get_misalign_bytes(const ggml_backend_vk_context * ctx, const gg
     return ((vk_tensor_offset(t) + t->view_offs) & (ctx->device->properties.limits.minStorageBufferOffsetAlignment - 1));;
 }
 
+static uint32_t ggml_vk_concat_unit_size(ggml_type type) {
+    const uint32_t type_size = ggml_type_size(type);
+
+    if (!ggml_is_quantized(type)) {
+        return type_size;
+    }
+
+    // Use the widest existing concat shader that evenly divides a quant block.
+    if (type_size % 8 == 0) {
+        return 8;
+    }
+    if (type_size % 4 == 0) {
+        return 4;
+    }
+    if (type_size % 2 == 0) {
+        return 2;
+    }
+    return 1;
+}
+
+static bool ggml_vk_concat_supported(const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * dst) {
+    if (src0->type != src1->type || src0->type != dst->type) {
+        return false;
+    }
+
+    if (!ggml_is_quantized(src0->type)) {
+        const size_t type_size = ggml_type_size(src0->type);
+        return type_size == 1 || type_size == 2 || type_size == 4 || type_size == 8;
+    }
+
+    // Quantized tensor rows are block-aligned when created.
+    return ggml_is_contiguous_rows(src0) && ggml_is_contiguous_rows(src1) && ggml_is_contiguous_rows(dst);
+}
+
 template <typename T> void init_pushconst_tensor_offsets(ggml_backend_vk_context * ctx, T &p, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, const ggml_tensor * src3, ggml_tensor * dst) {
     GGML_UNUSED(p);
     GGML_UNUSED(src0);
@@ -10896,14 +10935,10 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
         }
         return nullptr;
     case GGML_OP_CONCAT: {
-        if (src0->type != src1->type || src0->type != dst->type) {
+        if (!ggml_vk_concat_supported(src0, src1, dst)) {
             return nullptr;
         }
-        if (ggml_blck_size(src0->type) != 1) {
-            return nullptr;
-        }
-        const size_t type_size = ggml_type_size(src0->type);
-        switch (type_size) {
+        switch (ggml_vk_concat_unit_size(src0->type)) {
         case 1:
             return ctx->device->pipeline_concat_i8;
         case 2:
@@ -11595,6 +11630,18 @@ template <> void init_pushconst_tensor_offsets(ggml_backend_vk_context * ctx, vk
     GGML_UNUSED(src3);
 }
 
+template <> void init_pushconst_tensor_offsets(ggml_backend_vk_context * ctx, vk_op_concat_push_constants &p, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, const ggml_tensor * src3, ggml_tensor * dst) {
+    const uint32_t unit_size = ggml_vk_concat_unit_size(dst->type);
+    const uint32_t a_offset = get_misalign_bytes(ctx, src0) / unit_size;
+    const uint32_t b_offset = get_misalign_bytes(ctx, src1) / unit_size;
+    const uint32_t d_offset = get_misalign_bytes(ctx, dst) / unit_size;
+
+    p.misalign_offsets = (a_offset << 16) | (b_offset << 8) | d_offset;
+
+    GGML_UNUSED(src2);
+    GGML_UNUSED(src3);
+}
+
 template <> void init_pushconst_tensor_offsets(ggml_backend_vk_context * ctx, vk_op_upscale_push_constants &p, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, const ggml_tensor * src3, ggml_tensor * dst) {
     const uint32_t a_offset = get_misalign_bytes(ctx, src0) / ggml_type_size(src0->type);
     const uint32_t d_offset = get_misalign_bytes(ctx, dst) / ggml_type_size(dst->type);
@@ -11630,7 +11677,7 @@ static void ggml_vk_op_f32(ggml_backend_vk_context * ctx, vk_context& subctx, co
     }
     std::cerr << "), (" << dst << ", name=" << dst->name << ", type=" << dst->type << ", ne0=" << dst->ne[0] << ", ne1=" << dst->ne[1] << ", ne2=" << dst->ne[2] << ", ne3=" << dst->ne[3] << ", nb0=" << dst->nb[0] << ", nb1=" << dst->nb[1] << ", nb2=" << dst->nb[2] << ", nb3=" << dst->nb[3];
     std::cerr << "), " << ggml_op_name(op) << ")");
-    GGML_ASSERT(op == GGML_OP_GET_ROWS || op == GGML_OP_CPY || (!ggml_is_quantized(src0->type) && (src1 == nullptr || !ggml_is_quantized(src1->type))));  // NOLINT
+    GGML_ASSERT(op == GGML_OP_GET_ROWS || op == GGML_OP_CPY || op == GGML_OP_CONCAT || (!ggml_is_quantized(src0->type) && (src1 == nullptr || !ggml_is_quantized(src1->type))));  // NOLINT
     GGML_ASSERT(dst->buffer != nullptr);
     const uint64_t ne00 = src0->ne[0];
     const uint64_t ne01 = src0->ne[1];
@@ -11885,6 +11932,9 @@ static void ggml_vk_op_f32(ggml_backend_vk_context * ctx, vk_context& subctx, co
                     ne *= ggml_type_size(src0->type) / 2;
                 }
             }
+            if (op == GGML_OP_CONCAT && ggml_is_quantized(dst->type)) {
+                ne = ne / ggml_blck_size(dst->type) * ggml_type_size(dst->type) / ggml_vk_concat_unit_size(dst->type);
+            }
             // copy_to_quant has block size of 32, and each thread does QUANT_K elements.
             // Splitting into 512x512xZ wouldn't work well since each workgroup does 1024 elements.
             // So divide by block size here before splitting into 512x512 groups.
@@ -12525,18 +12575,28 @@ static void ggml_vk_opt_step_sgd(ggml_backend_vk_context * ctx, vk_context& subc
 static void ggml_vk_concat(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
     int * op_params = (int *)dst->op_params;
 
-    const uint32_t src0_type_size = ggml_type_size(src0->type);
-    const uint32_t src1_type_size = ggml_type_size(src1->type);
-    const uint32_t dst_type_size = ggml_type_size(dst->type);
+    const uint32_t unit_size = ggml_vk_concat_unit_size(dst->type);
+    const uint32_t units_per_block = ggml_type_size(dst->type) / unit_size;
+    const uint32_t block_size = ggml_blck_size(dst->type);
+    const bool quantized = ggml_is_quantized(dst->type);
 
-    ggml_vk_op_f32<vk_op_binary_push_constants>(ctx, subctx, src0, src1, nullptr, nullptr, dst, GGML_OP_CONCAT, {
-        (uint32_t)ggml_nelements(dst),
-        (uint32_t)src0->ne[0], (uint32_t)src0->ne[1], (uint32_t)src0->ne[2],(uint32_t)src0->ne[3], (uint32_t)src0->nb[0] / src0_type_size, (uint32_t)src0->nb[1] / src0_type_size, (uint32_t)src0->nb[2] / src0_type_size, (uint32_t)src0->nb[3] / src0_type_size,
-        (uint32_t)src1->ne[0], (uint32_t)src1->ne[1], (uint32_t)src1->ne[2],(uint32_t)src1->ne[3], (uint32_t)src1->nb[0] / src1_type_size, (uint32_t)src1->nb[1] / src1_type_size, (uint32_t)src1->nb[2] / src1_type_size, (uint32_t)src1->nb[3] / src1_type_size,
-        (uint32_t) dst->ne[0], (uint32_t) dst->ne[1], (uint32_t) dst->ne[2],(uint32_t) dst->ne[3], (uint32_t) dst->nb[0] /  dst_type_size, (uint32_t) dst->nb[1] /  dst_type_size, (uint32_t) dst->nb[2] /  dst_type_size, (uint32_t) dst->nb[3] /  dst_type_size,
+    // Address dimension 0 in packed storage units; higher strides may be noncontiguous.
+    const uint32_t ne00 = src0->ne[0] / block_size * units_per_block;
+    const uint32_t ne10 = src1->ne[0] / block_size * units_per_block;
+    const uint32_t ne20 =  dst->ne[0] / block_size * units_per_block;
+    const uint32_t nb00 = quantized ? 1 : src0->nb[0] / unit_size;
+    const uint32_t nb10 = quantized ? 1 : src1->nb[0] / unit_size;
+    const uint32_t nb20 = quantized ? 1 :  dst->nb[0] / unit_size;
+
+    vk_op_concat_push_constants pc {{
+        ne20 * (uint32_t)dst->ne[1] * (uint32_t)dst->ne[2] * (uint32_t)dst->ne[3],
+        ne00, (uint32_t)src0->ne[1], (uint32_t)src0->ne[2],(uint32_t)src0->ne[3], nb00, (uint32_t)src0->nb[1] / unit_size, (uint32_t)src0->nb[2] / unit_size, (uint32_t)src0->nb[3] / unit_size,
+        ne10, (uint32_t)src1->ne[1], (uint32_t)src1->ne[2],(uint32_t)src1->ne[3], nb10, (uint32_t)src1->nb[1] / unit_size, (uint32_t)src1->nb[2] / unit_size, (uint32_t)src1->nb[3] / unit_size,
+        ne20, (uint32_t) dst->ne[1], (uint32_t) dst->ne[2],(uint32_t) dst->ne[3], nb20, (uint32_t) dst->nb[1] / unit_size, (uint32_t) dst->nb[2] / unit_size, (uint32_t) dst->nb[3] / unit_size,
         0,
         0.0f, 0.0f, op_params[0],
-    });
+    }};
+    ggml_vk_op_f32<vk_op_concat_push_constants>(ctx, subctx, src0, src1, nullptr, nullptr, dst, GGML_OP_CONCAT, std::move(pc));
 }
 
 static void ggml_vk_upscale(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst) {
@@ -17872,12 +17932,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
             return op->src[0]->type == op->src[1]->type && op->src[0]->type == op->type &&
                    (op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_I32);
         case GGML_OP_CONCAT: {
-            if (op->src[0]->type != op->src[1]->type || op->src[0]->type != op->type) {
-                return false;
-            }
-            const size_t type_size = ggml_type_size(op->type);
-            return ggml_blck_size(op->type) == 1 &&
-                   (type_size == 1 || type_size == 2 || type_size == 4 || type_size == 8);
+            return ggml_vk_concat_supported(op->src[0], op->src[1], op);
         }
         case GGML_OP_ADD1:
             return (op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_F32)