/bin/llama-server \
    --model unsloth/Qwen3-30B-A3B/Qwen3-30B-A3B-Q4_K_M.gguf \
    --threads 8 \
    --ctx-size 40960 \
    --n-gpu-layers 20 \
    --prio 2 \
    --temp 0.6 \
    --repeat-penalty 1.1 \
    --min-p 0.0 \
    --top-k 20 \
    --top-p 0.95 \
    --port 8080 --host 0.0.0.0

ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090 Laptop GPU, compute capability 8.9, VMM: yes
build: 5615 (f470bc36) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 8, n_threads_batch = 8, total_threads = 32

system_info: n_threads = 8 (n_threads_batch = 8) / 32 | CUDA : ARCHS = 890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 

main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8080, http threads: 31
main: loading model
srv    load_model: loading model '/.../unsloth/Qwen3-30B-A3B/Qwen3-30B-A3B-Q4_K_M.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090 Laptop GPU) - 12029 MiB free
llama_model_loader: loaded meta data with 35 key-value pairs and 579 tensors from /.../unsloth/Qwen3-30B-A3B/Qwen3-30B-A3B-Q4_K_M.gguf (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              = qwen3moe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-30B-A3B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3-30B-A3B
llama_model_loader: - kv   4:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   5:                         general.size_label str              = 30B-A3B
llama_model_loader: - kv   6:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   7:                       qwen3moe.block_count u32              = 48
llama_model_loader: - kv   8:                    qwen3moe.context_length u32              = 40960
llama_model_loader: - kv   9:                  qwen3moe.embedding_length u32              = 2048
llama_model_loader: - kv  10:               qwen3moe.feed_forward_length u32              = 6144
llama_model_loader: - kv  11:              qwen3moe.attention.head_count u32              = 32
llama_model_loader: - kv  12:           qwen3moe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  13:                    qwen3moe.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  14:  qwen3moe.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  15:                 qwen3moe.expert_used_count u32              = 8
llama_model_loader: - kv  16:              qwen3moe.attention.key_length u32              = 128
llama_model_loader: - kv  17:            qwen3moe.attention.value_length u32              = 128
llama_model_loader: - kv  18:                      qwen3moe.expert_count u32              = 128
llama_model_loader: - kv  19:        qwen3moe.expert_feed_forward_length u32              = 768
llama_model_loader: - kv  20:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  21:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  22:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  23:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  24:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - kv  30:                          general.file_type u32              = 15
llama_model_loader: - kv  31:                      quantize.imatrix.file str              = Qwen3-30B-A3B-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv  32:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-30B-A3B.txt
llama_model_loader: - kv  33:             quantize.imatrix.entries_count i32              = 384
llama_model_loader: - kv  34:              quantize.imatrix.chunks_count i32              = 685
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type q4_K:  289 tensors
llama_model_loader: - type q6_K:   49 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 17.28 GiB (4.86 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3moe
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 2048
print_info: n_layer          = 48
print_info: n_head           = 32
print_info: n_head_kv        = 4
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 8
print_info: n_embd_k_gqa     = 512
print_info: n_embd_v_gqa     = 512
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 6144
print_info: n_expert         = 128
print_info: n_expert_used    = 8
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 40960
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 30B.A3B
print_info: model params     = 30.53 B
print_info: general.name     = Qwen3-30B-A3B
print_info: n_ff_exp         = 768
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 11 ','
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151654 '<|vision_pad|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 20 repeating layers to GPU
load_tensors: offloaded 20/49 layers to GPU
load_tensors:   CPU_Mapped model buffer size = 10441.17 MiB
load_tensors:        CUDA0 model buffer size =  7250.17 MiB
...................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 40960
llama_context: n_ctx_per_seq = 40960
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context:        CPU  output buffer size =     0.58 MiB
llama_kv_cache_unified:        CPU KV buffer size =  2240.00 MiB
llama_kv_cache_unified:      CUDA0 KV buffer size =  1600.00 MiB
llama_kv_cache_unified: size = 3840.00 MiB ( 40960 cells,  48 layers,  1 seqs), K (f16): 1920.00 MiB, V (f16): 1920.00 MiB
llama_context:      CUDA0 compute buffer size =  2788.50 MiB
llama_context:  CUDA_Host compute buffer size =    84.01 MiB
llama_context: graph nodes  = 3222
llama_context: graph splits = 396 (with bs=512), 87 (with bs=1)
common_init_from_params: setting dry_penalty_last_n to ctx_size = 40960
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
srv          init: initializing slots, n_slots = 1
slot         init: id  0 | task -1 | new slot n_ctx_slot = 40960
main: model loaded