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: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes build: 7040 (92bb442ad) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) (0000:01:00.0) - 20238 MiB free llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) (0000:03:00.0) - 23060 MiB free llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /mnt/world8/AI/ToBench/Qwen3-4B-Instruct-2507-unsloth/Magic_Quant/GGUF/Qwen3-4B-Instruct-2507-unsloth-BF16.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 4B Instruct 2507 Unsloth llama_model_loader: - kv 3: general.version str = 2507 llama_model_loader: - kv 4: general.finetune str = Instruct-unsloth llama_model_loader: - kv 5: general.basename str = Qwen3 llama_model_loader: - kv 6: general.size_label str = 4B llama_model_loader: - kv 7: general.license str = apache-2.0 llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/Qwen3-4B-... llama_model_loader: - kv 9: general.base_model.count u32 = 1 llama_model_loader: - kv 10: general.base_model.0.name str = Qwen3 4B Instruct 2507 llama_model_loader: - kv 11: general.base_model.0.version str = 2507 llama_model_loader: - kv 12: general.base_model.0.organization str = Qwen llama_model_loader: - kv 13: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-4B-... llama_model_loader: - kv 14: general.tags arr[str,2] = ["unsloth", "text-generation"] llama_model_loader: - kv 15: qwen3.block_count u32 = 36 llama_model_loader: - kv 16: qwen3.context_length u32 = 262144 llama_model_loader: - kv 17: qwen3.embedding_length u32 = 2560 llama_model_loader: - kv 18: qwen3.feed_forward_length u32 = 9728 llama_model_loader: - kv 19: qwen3.attention.head_count u32 = 32 llama_model_loader: - kv 20: qwen3.attention.head_count_kv u32 = 8 llama_model_loader: - kv 21: qwen3.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 22: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 23: qwen3.attention.key_length u32 = 128 llama_model_loader: - kv 24: qwen3.attention.value_length u32 = 128 llama_model_loader: - kv 25: general.file_type u32 = 32 llama_model_loader: - kv 26: general.quantization_version u32 = 2 llama_model_loader: - kv 27: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 28: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 29: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 30: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 31: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 32: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 151654 llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 35: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - type f32: 145 tensors llama_model_loader: - type bf16: 253 tensors print_info: file format = GGUF V3 (latest) print_info: file type = BF16 print_info: file size = 7.49 GiB (16.00 BPW) load: printing all EOG tokens: load: - 151643 ('<|endoftext|>') load: - 151645 ('<|im_end|>') load: - 151662 ('<|fim_pad|>') load: - 151663 ('<|repo_name|>') load: - 151664 ('<|file_sep|>') 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 = 262144 print_info: n_embd = 2560 print_info: n_embd_inp = 2560 print_info: n_layer = 36 print_info: n_head = 32 print_info: n_head_kv = 8 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 = 4 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 = 9728 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: n_expert_groups = 0 print_info: n_group_used = 0 print_info: causal attn = 1 print_info: pooling type = -1 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 5000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 262144 print_info: rope_finetuned = unknown print_info: model type = 4B print_info: model params = 4.02 B print_info: general.name = Qwen3 4B Instruct 2507 Unsloth 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 20/37 layers to GPU load_tensors: CPU_Mapped model buffer size = 7672.62 MiB load_tensors: CUDA0 model buffer size = 1925.21 MiB load_tensors: CUDA1 model buffer size = 1925.21 MiB ............................................................................................ llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 2048 llama_context: n_ctx_seq = 2048 llama_context: n_batch = 2048 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = auto llama_context: kv_unified = false llama_context: freq_base = 5000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_seq (2048) < n_ctx_train (262144) -- the full capacity of the model will not be utilized llama_context: CPU output buffer size = 0.58 MiB llama_kv_cache: CPU KV buffer size = 128.00 MiB llama_kv_cache: CUDA0 KV buffer size = 80.00 MiB llama_kv_cache: CUDA1 KV buffer size = 80.00 MiB llama_kv_cache: size = 288.00 MiB ( 2048 cells, 36 layers, 1/1 seqs), K (f16): 144.00 MiB, V (f16): 144.00 MiB llama_context: Flash Attention was auto, set to enabled llama_context: CUDA0 compute buffer size = 1043.62 MiB llama_context: CUDA1 compute buffer size = 74.01 MiB llama_context: CUDA_Host compute buffer size = 9.01 MiB llama_context: graph nodes = 1267 llama_context: graph splits = 213 (with bs=512), 52 (with bs=1) common_init_from_params: added <|endoftext|> logit bias = -inf common_init_from_params: added <|im_end|> logit bias = -inf common_init_from_params: added <|fim_pad|> logit bias = -inf common_init_from_params: added <|repo_name|> logit bias = -inf common_init_from_params: added <|file_sep|> logit bias = -inf 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 = 16 (n_threads_batch = 16) / 32 | CUDA : ARCHS = 860 | 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 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | perplexity: tokenizing the input .. perplexity: tokenization took 113.111 ms perplexity: calculating perplexity over 44 chunks, n_ctx=2048, batch_size=2048, n_seq=1 perplexity: 1.91 seconds per pass - ETA 1.40 minutes [1]3.1376,[2]2.4676,[3]1.8269,[4]1.6835,[5]1.8008,[6]1.8530,[7]1.8077,[8]1.7792,[9]1.6971,[10]1.6416,[11]1.6086,[12]1.6100,[13]1.5762,[14]1.5537,[15]1.5752,[16]1.5533,[17]1.5403,[18]1.5472,[19]1.5330,[20]1.5133,[21]1.5054,[22]1.5018,[23]1.5232,[24]1.5104,[25]1.5159,[26]1.4986,[27]1.4894,[28]1.4877,[29]1.5031,[30]1.5066,[31]1.4966,[32]1.4860,[33]1.4888,[34]1.4862,[35]1.4855,[36]1.5124,[37]1.5227,[38]1.5284,[39]1.5357,[40]1.5368,[41]1.5303,[42]1.5446,[43]1.5461,[44]1.5469, Final estimate: PPL = 1.5469 +/- 0.01221 llama_perf_context_print: load time = 2838.89 ms llama_perf_context_print: prompt eval time = 72265.76 ms / 90112 tokens ( 0.80 ms per token, 1246.95 tokens per second) llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 73518.07 ms / 90113 tokens llama_perf_context_print: graphs reused = 0 llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | llama_memory_breakdown_print: | - CUDA0 (RTX 3090) | 24115 = 16994 + (3048 = 1925 + 80 + 1043) + 4072 | llama_memory_breakdown_print: | - CUDA1 (RTX 3090) | 24124 = 20866 + (2079 = 1925 + 80 + 74) + 1178 | llama_memory_breakdown_print: | - Host | 7809 = 7672 + 128 + 9 |