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) - 21487 MiB free llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) (0000:03:00.0) - 23582 MiB free llama_model_loader: loaded meta data with 36 key-value pairs and 399 tensors from /mnt/world8/AI/Models/Qwen3-VL-8B-Thinking-unsloth/GGUF/Qwen3-VL-8B-Thinking-unsloth-Q6_K.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 = qwen3vl llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 VL 8B Thinking Unsloth llama_model_loader: - kv 3: general.finetune str = Thinking-unsloth llama_model_loader: - kv 4: general.basename str = Qwen3-VL llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Qwen3 VL 8B Thinking llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-VL-... llama_model_loader: - kv 11: general.tags arr[str,2] = ["unsloth", "image-text-to-text"] llama_model_loader: - kv 12: qwen3vl.block_count u32 = 36 llama_model_loader: - kv 13: qwen3vl.context_length u32 = 262144 llama_model_loader: - kv 14: qwen3vl.embedding_length u32 = 4096 llama_model_loader: - kv 15: qwen3vl.feed_forward_length u32 = 12288 llama_model_loader: - kv 16: qwen3vl.attention.head_count u32 = 32 llama_model_loader: - kv 17: qwen3vl.attention.head_count_kv u32 = 8 llama_model_loader: - kv 18: qwen3vl.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 19: qwen3vl.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 20: qwen3vl.attention.key_length u32 = 128 llama_model_loader: - kv 21: qwen3vl.attention.value_length u32 = 128 llama_model_loader: - kv 22: qwen3vl.rope.dimension_sections arr[i32,4] = [24, 20, 20, 0] llama_model_loader: - kv 23: qwen3vl.n_deepstack_layers u32 = 3 llama_model_loader: - kv 24: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 25: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 28: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 30: tokenizer.ggml.padding_token_id u32 = 151654 llama_model_loader: - kv 31: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 33: tokenizer.chat_template str = {# Unsloth template fixes #}\n{%- set ... llama_model_loader: - kv 34: general.quantization_version u32 = 2 llama_model_loader: - kv 35: general.file_type u32 = 18 llama_model_loader: - type f32: 145 tensors llama_model_loader: - type q6_K: 254 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q6_K print_info: file size = 6.26 GiB (6.56 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 = qwen3vl print_info: vocab_only = 0 print_info: n_ctx_train = 262144 print_info: n_embd = 4096 print_info: n_embd_inp = 16384 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 = 12288 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 = 0 print_info: rope type = 40 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: mrope sections = [24, 20, 20, 0] print_info: model type = 8B print_info: model params = 8.19 B print_info: general.name = Qwen3 VL 8B Thinking Unsloth print_info: vocab type = BPE print_info: n_vocab = 151936 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' 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 = 3389.24 MiB load_tensors: CUDA0 model buffer size = 1509.70 MiB load_tensors: CUDA1 model buffer size = 1509.70 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 = 791.61 MiB llama_context: CUDA1 compute buffer size = 98.02 MiB llama_context: CUDA_Host compute buffer size = 12.02 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 112.18 ms perplexity: calculating perplexity over 44 chunks, n_ctx=2048, batch_size=2048, n_seq=1 perplexity: 1.73 seconds per pass - ETA 1.27 minutes [1]2.6517,[2]2.1077,[3]1.6452,[4]1.5297,[5]1.6208,[6]1.6785,[7]1.6389,[8]1.6186,[9]1.5511,[10]1.5087,[11]1.4810,[12]1.4859,[13]1.4582,[14]1.4409,[15]1.4535,[16]1.4366,[17]1.4233,[18]1.4259,[19]1.4141,[20]1.3990,[21]1.3931,[22]1.3904,[23]1.4115,[24]1.4014,[25]1.4063,[26]1.3932,[27]1.3851,[28]1.3828,[29]1.3967,[30]1.3980,[31]1.3887,[32]1.3808,[33]1.3815,[34]1.3798,[35]1.3784,[36]1.4017,[37]1.4113,[38]1.4162,[39]1.4231,[40]1.4241,[41]1.4191,[42]1.4325,[43]1.4325,[44]1.4333, Final estimate: PPL = 1.4333 +/- 0.00928 llama_perf_context_print: load time = 1152.75 ms llama_perf_context_print: prompt eval time = 66583.88 ms / 90112 tokens ( 0.74 ms per token, 1353.36 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 = 67758.91 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) | 24107 = 18974 + (2381 = 1509 + 80 + 791) + 2751 | llama_memory_breakdown_print: | - CUDA1 (RTX 3090) | 24124 = 21796 + (1687 = 1509 + 80 + 98) + 640 | llama_memory_breakdown_print: | - Host | 3529 = 3389 + 128 + 12 |