diff --git a/docs/development.md b/docs/development.md
index b1c944eed..e194dca0b 100644
--- a/docs/development.md
+++ b/docs/development.md
@@ -53,7 +53,7 @@ If both v11 and v12 tookkits are detected, runners for both major versions will
 
 #### Older Linux CUDA (NVIDIA)
 
-To support older GPUs with Compute Capability 3.5 or 3.7, you will need to use an older version of the Driver from [Unix Driver Archive](https://www.nvidia.com/en-us/drivers/unix/) (tested with 470) and [CUDA Toolkit Archive](https://developer.nvidia.com/cuda-toolkit-archive) (tested with cuda V11).  When you build Ollama, you will need to set two make variable to adjust the minimum compute capability Ollama supports via `make -j 5 CUDA_ARCHITECTURES="35;37;50;52" EXTRA_GOLDLAGS="\"-X=github.com/ollama/ollama/discover.CudaComputeMajorMin=3\" \"-X=github.com/ollama/ollama/discover.CudaComputeMinorMin=5\""`.  To find the Compute Capability of your older GPU, refer to [GPU Compute Capability](https://developer.nvidia.com/cuda-gpus).
+To support older GPUs with Compute Capability 3.5 or 3.7, you will need to use an older version of the Driver from [Unix Driver Archive](https://www.nvidia.com/en-us/drivers/unix/) (tested with 470) and [CUDA Toolkit Archive](https://developer.nvidia.com/cuda-toolkit-archive) (tested with cuda V11).  When you build Ollama, you will need to set two make variable to adjust the minimum compute capability Ollama supports via `make -j 5 CUDA_ARCHITECTURES="35;37;50;52" EXTRA_GOLDFLAGS="\"-X=github.com/ollama/ollama/discover.CudaComputeMajorMin=3\" \"-X=github.com/ollama/ollama/discover.CudaComputeMinorMin=5\""`.  To find the Compute Capability of your older GPU, refer to [GPU Compute Capability](https://developer.nvidia.com/cuda-gpus).
 
 #### Linux ROCm (AMD)
 
diff --git a/make/Makefile.ollama b/make/Makefile.ollama
index 51ef7713f..678ea0d55 100644
--- a/make/Makefile.ollama
+++ b/make/Makefile.ollama
@@ -6,7 +6,7 @@ exe: $(OLLAMA_EXE)
 dist_exe dist_ollama: $(DIST_OLLAMA_EXE)
 
 GO_DEPS=$(foreach dir,$(shell go list -deps -f '{{.Dir}}' . ),$(wildcard $(dir)/*.go))
-CPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(TARGET_CPU_FLAGS))\" $(EXTRA_GOLDLAGS) $(TARGET_LDFLAGS)"
+CPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(TARGET_CPU_FLAGS))\" $(EXTRA_GOLDFLAGS) $(TARGET_LDFLAGS)"
 
 $(OLLAMA_EXE) $(DIST_OLLAMA_EXE): TARGET_CPU_FLAGS=$(CUSTOM_CPU_FLAGS)
 $(OLLAMA_EXE) $(DIST_OLLAMA_EXE): $(COMMON_SRCS) $(COMMON_HDRS) $(GO_DEPS)
diff --git a/make/gpu.make b/make/gpu.make
index 9cfb45158..ef1c1345f 100644
--- a/make/gpu.make
+++ b/make/gpu.make
@@ -5,7 +5,7 @@ dummy:
 	$(error This makefile is not meant to build directly, but instead included in other Makefiles that set required variables)
 endif
 
-GPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(GPU_RUNNER_CPU_FLAGS))\" $(EXTRA_GOLDLAGS) $(TARGET_LDFLAGS)"
+GPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(GPU_RUNNER_CPU_FLAGS))\" $(EXTRA_GOLDFLAGS) $(TARGET_LDFLAGS)"
 
 # TODO Unify how we handle dependencies in the dist/packaging and install flow
 # today, cuda is bundled, but rocm is split out.  Should split them each out by runner