diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
index 217575871cb..024a16d49e0 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
@@ -1,23 +1,12 @@
 repo_id:
   - 'THUDM/chatglm3-6b'
-  - 'THUDM/chatglm2-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
   - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'internlm/internlm-chat-7b'
-  - 'Qwen/Qwen-7B-Chat'
-  - 'BAAI/AquilaChat2-7B'
   # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'WisdomShell/CodeShell-7B-Chat'
-  - 'tiiuae/falcon-7b-instruct-with-patch'
-  - 'mosaicml/mpt-7b-chat'
 #  - 'liuhaotian/llava-v1.5-7b' # Cannot load using AutoModelForCausalLM in 4.36+
-  - 'RWKV/rwkv-4-world-7b'
-  - 'RWKV/rwkv-5-world-7b'
-  - 'IEITYuan/Yuan2-2B-hf'
-  - 'mistralai/Mistral-7B-Instruct-v0.1'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
index 16189637a58..2257fd1f7ee 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
@@ -2,8 +2,6 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - '01-ai/Yi-6B-Chat'
-  - 'microsoft/phi-2'
   - 'microsoft/Phi-3-mini-4k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
index a073c5cb77c..527cefc95f9 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
@@ -1,22 +1,13 @@
 repo_id:
   - 'THUDM/chatglm3-6b'
-  - 'THUDM/chatglm2-6b'
   - 'baichuan-inc/Baichuan2-7B-Chat'
   - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'internlm/internlm-chat-7b'
-  - 'Qwen/Qwen-7B-Chat'
-  - 'BAAI/AquilaChat2-7B'
   # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'WisdomShell/CodeShell-7B-Chat'
-  - 'tiiuae/falcon-7b-instruct-with-patch'
-  - 'mosaicml/mpt-7b-chat'
 #  - 'liuhaotian/llava-v1.5-7b' # Cannot load using AutoModelForCausalLM in 4.36+
   # - 'RWKV/rwkv-4-world-7b'
   # - 'RWKV/rwkv-5-world-7b'
-  - 'IEITYuan/Yuan2-2B-hf'
-  - 'mistralai/Mistral-7B-Instruct-v0.1'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
index 5051de78de8..b31716ba4af 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
@@ -1,7 +1,6 @@
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
index 12d5fa7efd5..ffbaaa201a3 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
@@ -1,23 +1,12 @@
 repo_id:
   - 'THUDM/chatglm3-6b'
-  - 'THUDM/chatglm2-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
   - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'internlm/internlm-chat-7b'
-  - 'Qwen/Qwen-7B-Chat'
-  - 'BAAI/AquilaChat2-7B'
   # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'WisdomShell/CodeShell-7B-Chat'
-  - 'tiiuae/falcon-7b-instruct-with-patch'
-  - 'mosaicml/mpt-7b-chat'
 #  - 'liuhaotian/llava-v1.5-7b' # Cannot load using AutoModelForCausalLM in 4.36+
-  - 'RWKV/rwkv-4-world-7b'
-  - 'RWKV/rwkv-5-world-7b'
-  - 'IEITYuan/Yuan2-2B-hf'
-  - 'mistralai/Mistral-7B-Instruct-v0.1'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
index b9a29ddd863..9286f84dee8 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
@@ -2,8 +2,6 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - '01-ai/Yi-6B-Chat'
-  - 'microsoft/phi-2'
   - 'microsoft/Phi-3-mini-4k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/2048-256.yaml b/python/llm/test/benchmark/igpu-perf/2048-256.yaml
index b995c2949b1..aaf1d326293 100644
--- a/python/llm/test/benchmark/igpu-perf/2048-256.yaml
+++ b/python/llm/test/benchmark/igpu-perf/2048-256.yaml
@@ -1,23 +1,12 @@
 repo_id:
   - 'THUDM/chatglm3-6b'
-  - 'THUDM/chatglm2-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
   - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'internlm/internlm-chat-7b'
-  - 'Qwen/Qwen-7B-Chat'
-  - 'BAAI/AquilaChat2-7B'
   # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'WisdomShell/CodeShell-7B-Chat'
-  - 'tiiuae/falcon-7b-instruct-with-patch'
-  - 'mosaicml/mpt-7b-chat'
 #  - 'liuhaotian/llava-v1.5-7b' # Cannot load using AutoModelForCausalLM in 4.36+
-  - 'RWKV/rwkv-4-world-7b'
-  - 'RWKV/rwkv-5-world-7b'
-  - 'IEITYuan/Yuan2-2B-hf'
-  - 'mistralai/Mistral-7B-Instruct-v0.1'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3
diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
index c79f66166b2..264d60158d2 100644
--- a/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
@@ -2,8 +2,6 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - '01-ai/Yi-6B-Chat'
-  - 'microsoft/phi-2'
   - 'microsoft/Phi-3-mini-4k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/32-32.yaml b/python/llm/test/benchmark/igpu-perf/32-32.yaml
index 9ac123ec43b..f91210f6e95 100644
--- a/python/llm/test/benchmark/igpu-perf/32-32.yaml
+++ b/python/llm/test/benchmark/igpu-perf/32-32.yaml
@@ -1,23 +1,12 @@
 repo_id:
   - 'THUDM/chatglm3-6b'
-  - 'THUDM/chatglm2-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
   - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'internlm/internlm-chat-7b'
-  - 'Qwen/Qwen-7B-Chat'
-  - 'BAAI/AquilaChat2-7B'
   # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'WisdomShell/CodeShell-7B-Chat'
-  - 'tiiuae/falcon-7b-instruct-with-patch'
-  - 'mosaicml/mpt-7b-chat'
 #  - 'liuhaotian/llava-v1.5-7b' # Cannot load using AutoModelForCausalLM in 4.36+
-  - 'RWKV/rwkv-4-world-7b'
-  - 'RWKV/rwkv-5-world-7b'
-  - 'IEITYuan/Yuan2-2B-hf'
-  - 'mistralai/Mistral-7B-Instruct-v0.1'
 local_model_hub: 'path to your local model hub'
 warm_up: 3
 num_trials: 5
diff --git a/python/llm/test/benchmark/igpu-perf/32-32_437.yaml b/python/llm/test/benchmark/igpu-perf/32-32_437.yaml
index 13e70940433..9548c4a6c05 100644
--- a/python/llm/test/benchmark/igpu-perf/32-32_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/32-32_437.yaml
@@ -2,8 +2,6 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - '01-ai/Yi-6B-Chat'
-  - 'microsoft/phi-2'
   - 'microsoft/Phi-3-mini-4k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 3