github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5431] out of memory error when running mixtral:8x22b #49911

New Issue
Closed
opened 2026-04-28 13:23:19 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 13:23:19 -05:00
Owner
Copy Link

Originally created by @Marten-Ka on GitHub (Jul 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5431

What is the issue?

GPU: Nvidia GeForce RTX 2070 (7.5 GB)
RAM: 16 GB

Problem:
I've pulled mixtral:8x22b (ollama pull) and would like to run it. After typing ollama run mixtral:8x22b the process terminates with Error: llama runner process has terminated: exit status 0xc0000409
When looking in the server.log I can see that it fails with the memory error and tells me that it couldn't allocate enough memory.
I've read a lot of issues here and the workaround to limit OLLAMA_MAX_VRAM (limited to 6 GB) didn't help either.

Could you please explain whats the error and how I could handle it? Many thanks in advance!

Log:
2024/07/02 10:51:58 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:6000000000 OLLAMA_MODELS:C:\Users\-----\.ollama\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\-----\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-02T10:51:58.666+02:00 level=INFO source=images.go:730 msg="total blobs: 5"
time=2024-07-02T10:51:58.668+02:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0"
time=2024-07-02T10:51:58.671+02:00 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.48)"
time=2024-07-02T10:51:58.674+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]"
time=2024-07-02T10:51:58.856+02:00 level=INFO source=types.go:98 msg="inference compute" id=GPU-9b341200-a290-ff84-3a34-412d81b35c4f library=cuda compute=7.5 driver=12.5 name="NVIDIA GeForce RTX 2070 SUPER" total="8.0 GiB" available="7.0 GiB"
[GIN] 2024/07/02 - 10:51:58 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/02 - 10:51:58 | 200 | 21.6534ms | 127.0.0.1 | POST "/api/show"
time=2024-07-02T10:51:58.970+02:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=57 layers.offload=3 layers.split="" memory.available="[7.6 GiB]" memory.required.full="77.5 GiB" memory.required.partial="7.1 GiB" memory.required.kv="448.0 MiB" memory.required.allocations="[7.1 GiB]" memory.weights.total="74.2 GiB" memory.weights.repeating="74.1 GiB" memory.weights.nonrepeating="157.5 MiB" memory.graph.full="244.0 MiB" memory.graph.partial="1.3 GiB"
time=2024-07-02T10:51:58.981+02:00 level=INFO source=server.go:368 msg="starting llama server" cmd="C:\Users\-----\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe --model C:\Users\-----\.ollama\models\blobs\sha256-d0eeef8264ce10a7e578789ee69986c66425639e72c9855e36a0345c230918c9 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 3 --no-mmap --parallel 1 --port 51455"
time=2024-07-02T10:51:59.007+02:00 level=INFO source=sched.go:382 msg="loaded runners" count=1
time=2024-07-02T10:51:59.007+02:00 level=INFO source=server.go:556 msg="waiting for llama runner to start responding"
time=2024-07-02T10:51:59.008+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3171 commit="7c26775a" tid="6888" timestamp=1719910319
INFO [wmain] system info | n_threads=4 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="6888" timestamp=1719910319 total_threads=8
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="51455" tid="6888" timestamp=1719910319
llama_model_loader: loaded meta data with 28 key-value pairs and 563 tensors from C:\Users-----.ollama\models\blobs\sha256-d0eeef8264ce10a7e578789ee69986c66425639e72c9855e36a0345c230918c9 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = Mixtral-8x22B-Instruct-v0.1
llama_model_loader: - kv 2: llama.block_count u32 = 56
llama_model_loader: - kv 3: llama.context_length u32 = 65536
llama_model_loader: - kv 4: llama.embedding_length u32 = 6144
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 16384
llama_model_loader: - kv 6: llama.attention.head_count u32 = 48
llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 8: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: llama.expert_count u32 = 8
llama_model_loader: - kv 11: llama.expert_used_count u32 = 2
llama_model_loader: - kv 12: general.file_type u32 = 2
llama_model_loader: - kv 13: llama.vocab_size u32 = 32768
llama_model_loader: - kv 14: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 15: tokenizer.ggml.model str = llama
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,32768] = ["", "", "", "[INST]", "[...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,32768] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,32768] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 24: tokenizer.chat_template.tool_use str = {{bos_token}}{% set user_messages = m...
llama_model_loader: - kv 25: tokenizer.chat_templates arr[str,1] = ["tool_use"]
llama_model_loader: - kv 26: tokenizer.chat_template str = {{bos_token}}{% for message in messag...
llama_model_loader: - kv 27: general.quantization_version u32 = 2
llama_model_loader: - type f32: 113 tensors
llama_model_loader: - type f16: 56 tensors
llama_model_loader: - type q4_0: 281 tensors
llama_model_loader: - type q8_0: 112 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens cache size = 259
llm_load_vocab: token to piece cache size = 0.1732 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32768
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 65536
llm_load_print_meta: n_embd = 6144
llm_load_print_meta: n_head = 48
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 56
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 6
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 16384
llm_load_print_meta: n_expert = 8
llm_load_print_meta: n_expert_used = 2
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 65536
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: model type = 8x22B
llm_load_print_meta: model ftype = Q4_0
llm_load_print_meta: model params = 140.63 B
llm_load_print_meta: model size = 74.05 GiB (4.52 BPW)
llm_load_print_meta: general.name = Mixtral-8x22B-Instruct-v0.1
llm_load_print_meta: BOS token = 1 ''
llm_load_print_meta: EOS token = 2 ''
llm_load_print_meta: UNK token = 0 ''
llm_load_print_meta: LF token = 781 '<0x0A>'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 2070 SUPER, compute capability 7.5, VMM: yes
llm_load_tensors: ggml ctx size = 0.56 MiB
ggml_cuda_host_malloc: failed to allocate 71783.23 MiB of pinned memory: out of memory
ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 75270168608
llama_model_load: error loading model: unable to allocate backend buffer
llama_load_model_from_file: exception loading model
time=2024-07-02T10:51:59.625+02:00 level=ERROR source=sched.go:388 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 "
[GIN] 2024/07/02 - 10:51:59 | 500 | 707.5768ms | 127.0.0.1 | POST "/api/chat"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.48

Originally created by @Marten-Ka on GitHub (Jul 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5431 ### What is the issue? **GPU:** Nvidia GeForce RTX 2070 (7.5 GB) **RAM:** 16 GB **Problem:** I've pulled mixtral:8x22b (`ollama pull`) and would like to run it. After typing `ollama run mixtral:8x22b` the process terminates with Error: llama runner process has terminated: exit status 0xc0000409 When looking in the server.log I can see that it fails with the memory error and tells me that it couldn't allocate enough memory. I've read a lot of issues here and the workaround to limit OLLAMA_MAX_VRAM (limited to 6 GB) didn't help either. Could you please explain whats the error and how I could handle it? Many thanks in advance! **Log:** 2024/07/02 10:51:58 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:6000000000 OLLAMA_MODELS:C:\\Users\\-----\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\-----\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-02T10:51:58.666+02:00 level=INFO source=images.go:730 msg="total blobs: 5" time=2024-07-02T10:51:58.668+02:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0" time=2024-07-02T10:51:58.671+02:00 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.48)" time=2024-07-02T10:51:58.674+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]" time=2024-07-02T10:51:58.856+02:00 level=INFO source=types.go:98 msg="inference compute" id=GPU-9b341200-a290-ff84-3a34-412d81b35c4f library=cuda compute=7.5 driver=12.5 name="NVIDIA GeForce RTX 2070 SUPER" total="8.0 GiB" available="7.0 GiB" [GIN] 2024/07/02 - 10:51:58 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/02 - 10:51:58 | 200 | 21.6534ms | 127.0.0.1 | POST "/api/show" time=2024-07-02T10:51:58.970+02:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=57 layers.offload=3 layers.split="" memory.available="[7.6 GiB]" memory.required.full="77.5 GiB" memory.required.partial="7.1 GiB" memory.required.kv="448.0 MiB" memory.required.allocations="[7.1 GiB]" memory.weights.total="74.2 GiB" memory.weights.repeating="74.1 GiB" memory.weights.nonrepeating="157.5 MiB" memory.graph.full="244.0 MiB" memory.graph.partial="1.3 GiB" time=2024-07-02T10:51:58.981+02:00 level=INFO source=server.go:368 msg="starting llama server" cmd="C:\\Users\\-----\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cuda_v11.3\\ollama_llama_server.exe --model C:\\Users\\-----\\.ollama\\models\\blobs\\sha256-d0eeef8264ce10a7e578789ee69986c66425639e72c9855e36a0345c230918c9 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 3 --no-mmap --parallel 1 --port 51455" time=2024-07-02T10:51:59.007+02:00 level=INFO source=sched.go:382 msg="loaded runners" count=1 time=2024-07-02T10:51:59.007+02:00 level=INFO source=server.go:556 msg="waiting for llama runner to start responding" time=2024-07-02T10:51:59.008+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3171 commit="7c26775a" tid="6888" timestamp=1719910319 INFO [wmain] system info | n_threads=4 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="6888" timestamp=1719910319 total_threads=8 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="51455" tid="6888" timestamp=1719910319 llama_model_loader: loaded meta data with 28 key-value pairs and 563 tensors from C:\Users\-----\.ollama\models\blobs\sha256-d0eeef8264ce10a7e578789ee69986c66425639e72c9855e36a0345c230918c9 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = Mixtral-8x22B-Instruct-v0.1 llama_model_loader: - kv 2: llama.block_count u32 = 56 llama_model_loader: - kv 3: llama.context_length u32 = 65536 llama_model_loader: - kv 4: llama.embedding_length u32 = 6144 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 16384 llama_model_loader: - kv 6: llama.attention.head_count u32 = 48 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.expert_count u32 = 8 llama_model_loader: - kv 11: llama.expert_used_count u32 = 2 llama_model_loader: - kv 12: general.file_type u32 = 2 llama_model_loader: - kv 13: llama.vocab_size u32 = 32768 llama_model_loader: - kv 14: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 15: tokenizer.ggml.model str = llama llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,32768] = ["<unk>", "<s>", "</s>", "[INST]", "[... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,32768] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,32768] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template.tool_use str = {{bos_token}}{% set user_messages = m... llama_model_loader: - kv 25: tokenizer.chat_templates arr[str,1] = ["tool_use"] llama_model_loader: - kv 26: tokenizer.chat_template str = {{bos_token}}{% for message in messag... llama_model_loader: - kv 27: general.quantization_version u32 = 2 llama_model_loader: - type f32: 113 tensors llama_model_loader: - type f16: 56 tensors llama_model_loader: - type q4_0: 281 tensors llama_model_loader: - type q8_0: 112 tensors llama_model_loader: - type q6_K: 1 tensors llm_load_vocab: special tokens cache size = 259 llm_load_vocab: token to piece cache size = 0.1732 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32768 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 65536 llm_load_print_meta: n_embd = 6144 llm_load_print_meta: n_head = 48 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 56 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 6 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 16384 llm_load_print_meta: n_expert = 8 llm_load_print_meta: n_expert_used = 2 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 65536 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: model type = 8x22B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 140.63 B llm_load_print_meta: model size = 74.05 GiB (4.52 BPW) llm_load_print_meta: general.name = Mixtral-8x22B-Instruct-v0.1 llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: LF token = 781 '<0x0A>' ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 2070 SUPER, compute capability 7.5, VMM: yes llm_load_tensors: ggml ctx size = 0.56 MiB ggml_cuda_host_malloc: failed to allocate 71783.23 MiB of pinned memory: out of memory ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 75270168608 llama_model_load: error loading model: unable to allocate backend buffer llama_load_model_from_file: exception loading model time=2024-07-02T10:51:59.625+02:00 level=ERROR source=sched.go:388 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 " [GIN] 2024/07/02 - 10:51:59 | 500 | 707.5768ms | 127.0.0.1 | POST "/api/chat" ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.48
GiteaMirror added the bug label 2026-04-28 13:23:19 -05:00
GiteaMirror commented 2026-04-28 13:23:23 -05:00
Author
Owner
Copy Link

@bearjaws commented on GitHub (Jul 2, 2024):

I believe you need a much smaller quantization to run that model. IIRC the default 8x22 from ollama run mixtral:8x22b needs 32GiB combined vram+system memory to make it work, so at 22GiB you are not going to be able to run it.

You could try a Q2 version but the quality is going to go down significantly. Does something smaller like llama3 work without issue?

<!-- gh-comment-id:2203036120 --> @bearjaws commented on GitHub (Jul 2, 2024): I believe you need a much smaller quantization to run that model. IIRC the default 8x22 from `ollama run mixtral:8x22b` needs 32GiB combined vram+system memory to make it work, so at 22GiB you are not going to be able to run it. You could try a Q2 version but the quality is going to go down significantly. Does something smaller like llama3 work without issue?
GiteaMirror commented 2026-04-28 13:23:25 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 2, 2024):

This is a dup of #4955 - you're attempting to load a model that requires ~77G on a system that has a total of ~23G (VRAM + system memory) which wont work. Once we resolve that issue we'll report a better error message instead of trying to load the model and failing. As @bearjaws mentioned above, you'll need to try a smaller model on your system, ideally one that fits in the ~7G of VRAM for optimal performance.

<!-- gh-comment-id:2204398444 --> @dhiltgen commented on GitHub (Jul 2, 2024): This is a dup of #4955 - you're attempting to load a model that requires ~77G on a system that has a total of ~23G (VRAM + system memory) which wont work. Once we resolve that issue we'll report a better error message instead of trying to load the model and failing. As @bearjaws mentioned above, you'll need to try a smaller model on your system, ideally one that fits in the ~7G of VRAM for optimal performance.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#49911
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?