ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 CUDA devices:
  Device 0: Tesla T4, compute capability 7.5, VMM: yes
  Device 1: Tesla T4, compute capability 7.5, VMM: yes
build: 5273 (8ae5ebcf) with gcc-14 (Homebrew GCC 14.2.0_1) 14.2.0 for x86_64-pc-linux-gnu
llama_model_load_from_file_impl: using device CUDA0 (Tesla T4) - 14992 MiB free
llama_model_load_from_file_impl: using device CUDA1 (Tesla T4) - 14992 MiB free
llama_model_loader: loaded meta data with 32 key-value pairs and 707 tensors from /root/Qwen3-32B-UD-Q4_K_XL.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              = qwen3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-32B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3-32B
llama_model_loader: - kv   4:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   5:                         general.size_label str              = 32B
llama_model_loader: - kv   6:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   7:                          qwen3.block_count u32              = 64
llama_model_loader: - kv   8:                       qwen3.context_length u32              = 40960
llama_model_loader: - kv   9:                     qwen3.embedding_length u32              = 5120
llama_model_loader: - kv  10:                  qwen3.feed_forward_length u32              = 25600
llama_model_loader: - kv  11:                 qwen3.attention.head_count u32              = 64
llama_model_loader: - kv  12:              qwen3.attention.head_count_kv u32              = 8
llama_model_loader: - kv  13:                       qwen3.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  14:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  15:                 qwen3.attention.key_length u32              = 128
llama_model_loader: - kv  16:               qwen3.attention.value_length u32              = 128
llama_model_loader: - kv  17:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  18:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  19:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  20:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  21:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  22:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  23:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  24:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - kv  27:                          general.file_type u32              = 15
llama_model_loader: - kv  28:                      quantize.imatrix.file str              = Qwen3-32B-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv  29:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-32B.txt
llama_model_loader: - kv  30:             quantize.imatrix.entries_count i32              = 448
llama_model_loader: - kv  31:              quantize.imatrix.chunks_count i32              = 32
llama_model_loader: - type  f32:  257 tensors
llama_model_loader: - type q4_K:  293 tensors
llama_model_loader: - type q5_K:   35 tensors
llama_model_loader: - type q6_K:   94 tensors
llama_model_loader: - type iq4_xs:   28 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 18.64 GiB (4.89 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 5120
print_info: n_layer          = 64
print_info: n_head           = 64
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
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     = 1024
print_info: n_embd_v_gqa     = 1024
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             = 25600
print_info: n_expert         = 0
print_info: n_expert_used    = 0
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       = 32B
print_info: model params     = 32.76 B
print_info: general.name     = Qwen3-32B
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 64 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 65/65 layers to GPU
load_tensors:  CUDA0_Split model buffer size =  9285.39 MiB
load_tensors:  CUDA1_Split model buffer size =  9383.22 MiB
load_tensors:        CUDA0 model buffer size =     1.32 MiB
load_tensors:        CUDA1 model buffer size =     1.26 MiB
load_tensors:   CPU_Mapped model buffer size =   417.30 MiB
................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 4
llama_context: n_ctx         = 2048
llama_context: n_ctx_per_seq = 512
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: n_ctx_per_seq (512) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     2.32 MiB
llama_kv_cache_unified: kv_size = 2048, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1, padding = 32
llama_kv_cache_unified:      CUDA0 KV buffer size =   264.00 MiB
llama_kv_cache_unified:      CUDA1 KV buffer size =   248.00 MiB
llama_kv_cache_unified: KV self size  =  512.00 MiB, K (f16):  256.00 MiB, V (f16):  256.00 MiB
llama_context:      CUDA0 compute buffer size =   312.00 MiB
llama_context:      CUDA1 compute buffer size =   312.00 MiB
llama_context:  CUDA_Host compute buffer size =    14.01 MiB
llama_context: graph nodes  = 2438
llama_context: graph splits = 3
common_init_from_params: setting dry_penalty_last_n to ctx_size = 2048
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)

system_info: n_threads = 2 (n_threads_batch = 2) / 4 | CUDA : ARCHS = 750 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 | 
perplexity: tokenizing the input ..
perplexity: tokenization took 786.684 ms
perplexity: calculating perplexity over 528 chunks, n_ctx=512, batch_size=2048, n_seq=4
perplexity: 7.88 seconds per pass - ETA 17.32 minutes
[1]nan,[2]nan,[3]nan,[4]nan,[5]nan,[6]nan,[7]nan,[8]nan,^C