koboldcpp/tools/cli

llama.cpp/tools/cli

Usage

Common params

Argument	Explanation
-h, --help, --usage	print usage and exit
--version	show version and build info
--license	show source code license and dependencies
-cl, --cache-list	show list of models in cache
--completion-bash	print source-able bash completion script for llama.cpp
--verbose-prompt	print a verbose prompt before generation (default: false)
-t, --threads N	number of CPU threads to use during generation (default: -1) (env: LLAMA_ARG_THREADS)
-tb, --threads-batch N	number of threads to use during batch and prompt processing (default: same as --threads)
-C, --cpu-mask M	CPU affinity mask: arbitrarily long hex. Complements cpu-range (default: "")
-Cr, --cpu-range lo-hi	range of CPUs for affinity. Complements --cpu-mask
--cpu-strict <0|1>	use strict CPU placement (default: 0)
--prio N	set process/thread priority : low(-1), normal(0), medium(1), high(2), realtime(3) (default: 0)
--poll <0...100>	use polling level to wait for work (0 - no polling, default: 50)
-Cb, --cpu-mask-batch M	CPU affinity mask: arbitrarily long hex. Complements cpu-range-batch (default: same as --cpu-mask)
-Crb, --cpu-range-batch lo-hi	ranges of CPUs for affinity. Complements --cpu-mask-batch
--cpu-strict-batch <0|1>	use strict CPU placement (default: same as --cpu-strict)
--prio-batch N	set process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: 0)
--poll-batch <0|1>	use polling to wait for work (default: same as --poll)
-c, --ctx-size N	size of the prompt context (default: 0, 0 = loaded from model) (env: LLAMA_ARG_CTX_SIZE)
-n, --predict, --n-predict N	number of tokens to predict (default: -1, -1 = infinity) (env: LLAMA_ARG_N_PREDICT)
-b, --batch-size N	logical maximum batch size (default: 2048) (env: LLAMA_ARG_BATCH)
-ub, --ubatch-size N	physical maximum batch size (default: 512) (env: LLAMA_ARG_UBATCH)
--keep N	number of tokens to keep from the initial prompt (default: 0, -1 = all)
--swa-full	use full-size SWA cache (default: false) (more info) (env: LLAMA_ARG_SWA_FULL)
-fa, --flash-attn [on|off|auto]	set Flash Attention use ('on', 'off', or 'auto', default: 'auto') (env: LLAMA_ARG_FLASH_ATTN)
-p, --prompt PROMPT	prompt to start generation with; for system message, use -sys
--perf, --no-perf	whether to enable internal libllama performance timings (default: false) (env: LLAMA_ARG_PERF)
-f, --file FNAME	a file containing the prompt (default: none)
-bf, --binary-file FNAME	binary file containing the prompt (default: none)
-e, --escape, --no-escape	whether to process escapes sequences (\n, \r, \t, ', ", \) (default: true)
--rope-scaling {none,linear,yarn}	RoPE frequency scaling method, defaults to linear unless specified by the model (env: LLAMA_ARG_ROPE_SCALING_TYPE)
--rope-scale N	RoPE context scaling factor, expands context by a factor of N (env: LLAMA_ARG_ROPE_SCALE)
--rope-freq-base N	RoPE base frequency, used by NTK-aware scaling (default: loaded from model) (env: LLAMA_ARG_ROPE_FREQ_BASE)
--rope-freq-scale N	RoPE frequency scaling factor, expands context by a factor of 1/N (env: LLAMA_ARG_ROPE_FREQ_SCALE)
--yarn-orig-ctx N	YaRN: original context size of model (default: 0 = model training context size) (env: LLAMA_ARG_YARN_ORIG_CTX)
--yarn-ext-factor N	YaRN: extrapolation mix factor (default: -1.00, 0.0 = full interpolation) (env: LLAMA_ARG_YARN_EXT_FACTOR)
--yarn-attn-factor N	YaRN: scale sqrt(t) or attention magnitude (default: -1.00) (env: LLAMA_ARG_YARN_ATTN_FACTOR)
--yarn-beta-slow N	YaRN: high correction dim or alpha (default: -1.00) (env: LLAMA_ARG_YARN_BETA_SLOW)
--yarn-beta-fast N	YaRN: low correction dim or beta (default: -1.00) (env: LLAMA_ARG_YARN_BETA_FAST)
-kvo, --kv-offload, -nkvo, --no-kv-offload	whether to enable KV cache offloading (default: enabled) (env: LLAMA_ARG_KV_OFFLOAD)
--repack, -nr, --no-repack	whether to enable weight repacking (default: enabled) (env: LLAMA_ARG_REPACK)
--no-host	bypass host buffer allowing extra buffers to be used (env: LLAMA_ARG_NO_HOST)
-ctk, --cache-type-k TYPE	KV cache data type for K allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default: f16) (env: LLAMA_ARG_CACHE_TYPE_K)
-ctv, --cache-type-v TYPE	KV cache data type for V allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default: f16) (env: LLAMA_ARG_CACHE_TYPE_V)
-dt, --defrag-thold N	KV cache defragmentation threshold (DEPRECATED) (env: LLAMA_ARG_DEFRAG_THOLD)
-np, --parallel N	number of parallel sequences to decode (default: 1) (env: LLAMA_ARG_N_PARALLEL)
--mlock	force system to keep model in RAM rather than swapping or compressing (env: LLAMA_ARG_MLOCK)
--mmap, --no-mmap	whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock) (default: enabled) (env: LLAMA_ARG_MMAP)
-dio, --direct-io, -ndio, --no-direct-io	use DirectIO if available. (default: disabled) (env: LLAMA_ARG_DIO)
--numa TYPE	attempt optimizations that help on some NUMA systems - distribute: spread execution evenly over all nodes - isolate: only spawn threads on CPUs on the node that execution started on - numactl: use the CPU map provided by numactl if run without this previously, it is recommended to drop the system page cache before using this see https://github.com/ggml-org/llama.cpp/issues/1437 (env: LLAMA_ARG_NUMA)
-dev, --device <dev1,dev2,..>	comma-separated list of devices to use for offloading (none = don't offload) use --list-devices to see a list of available devices (env: LLAMA_ARG_DEVICE)
--list-devices	print list of available devices and exit
-ot, --override-tensor <tensor name pattern>=<buffer type>,...	override tensor buffer type (env: LLAMA_ARG_OVERRIDE_TENSOR)
-cmoe, --cpu-moe	keep all Mixture of Experts (MoE) weights in the CPU (env: LLAMA_ARG_CPU_MOE)
-ncmoe, --n-cpu-moe N	keep the Mixture of Experts (MoE) weights of the first N layers in the CPU (env: LLAMA_ARG_N_CPU_MOE)
-ngl, --gpu-layers, --n-gpu-layers N	max. number of layers to store in VRAM, either an exact number, 'auto', or 'all' (default: auto) (env: LLAMA_ARG_N_GPU_LAYERS)
-sm, --split-mode {none,layer,row}	how to split the model across multiple GPUs, one of: - none: use one GPU only - layer (default): split layers and KV across GPUs - row: split rows across GPUs (env: LLAMA_ARG_SPLIT_MODE)
-ts, --tensor-split N0,N1,N2,...	fraction of the model to offload to each GPU, comma-separated list of proportions, e.g. 3,1 (env: LLAMA_ARG_TENSOR_SPLIT)
-mg, --main-gpu INDEX	the GPU to use for the model (with split-mode = none), or for intermediate results and KV (with split-mode = row) (default: 0) (env: LLAMA_ARG_MAIN_GPU)
-fit, --fit [on|off]	whether to adjust unset arguments to fit in device memory ('on' or 'off', default: 'on') (env: LLAMA_ARG_FIT)
-fitt, --fit-target MiB0,MiB1,MiB2,...	target margin per device for --fit, comma-separated list of values, single value is broadcast across all devices, default: 1024 (env: LLAMA_ARG_FIT_TARGET)
-fitc, --fit-ctx N	minimum ctx size that can be set by --fit option, default: 4096 (env: LLAMA_ARG_FIT_CTX)
--check-tensors	check model tensor data for invalid values (default: false)
--override-kv KEY=TYPE:VALUE,...	advanced option to override model metadata by key. to specify multiple overrides, either use comma-separated values. types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false,tokenizer.ggml.add_eos_token=bool:false
--op-offload, --no-op-offload	whether to offload host tensor operations to device (default: true)
--lora FNAME	path to LoRA adapter (use comma-separated values to load multiple adapters)
--lora-scaled FNAME:SCALE,...	path to LoRA adapter with user defined scaling (format: FNAME:SCALE,...) note: use comma-separated values
--control-vector FNAME	add a control vector note: use comma-separated values to add multiple control vectors
--control-vector-scaled FNAME:SCALE,...	add a control vector with user defined scaling SCALE note: use comma-separated values (format: FNAME:SCALE,...)
--control-vector-layer-range START END	layer range to apply the control vector(s) to, start and end inclusive
-m, --model FNAME	model path to load (env: LLAMA_ARG_MODEL)
-mu, --model-url MODEL_URL	model download url (default: unused) (env: LLAMA_ARG_MODEL_URL)
-dr, --docker-repo [<repo>/]<model>[:quant]	Docker Hub model repository. repo is optional, default to ai/. quant is optional, default to :latest. example: gemma3 (default: unused) (env: LLAMA_ARG_DOCKER_REPO)
-hf, -hfr, --hf-repo <user>/<model>[:quant]	Hugging Face model repository; quant is optional, case-insensitive, default to Q4_K_M, or falls back to the first file in the repo if Q4_K_M doesn't exist. mmproj is also downloaded automatically if available. to disable, add --no-mmproj example: ggml-org/GLM-4.7-Flash-GGUF:Q4_K_M (default: unused) (env: LLAMA_ARG_HF_REPO)
-hfd, -hfrd, --hf-repo-draft <user>/<model>[:quant]	Same as --hf-repo, but for the draft model (default: unused) (env: LLAMA_ARG_HFD_REPO)
-hff, --hf-file FILE	Hugging Face model file. If specified, it will override the quant in --hf-repo (default: unused) (env: LLAMA_ARG_HF_FILE)
-hfv, -hfrv, --hf-repo-v <user>/<model>[:quant]	Hugging Face model repository for the vocoder model (default: unused) (env: LLAMA_ARG_HF_REPO_V)
-hffv, --hf-file-v FILE	Hugging Face model file for the vocoder model (default: unused) (env: LLAMA_ARG_HF_FILE_V)
-hft, --hf-token TOKEN	Hugging Face access token (default: value from HF_TOKEN environment variable) (env: HF_TOKEN)
--log-disable	Log disable
--log-file FNAME	Log to file (env: LLAMA_LOG_FILE)
--log-colors [on|off|auto]	Set colored logging ('on', 'off', or 'auto', default: 'auto') 'auto' enables colors when output is to a terminal (env: LLAMA_LOG_COLORS)
-v, --verbose, --log-verbose	Set verbosity level to infinity (i.e. log all messages, useful for debugging)
--offline	Offline mode: forces use of cache, prevents network access (env: LLAMA_OFFLINE)
-lv, --verbosity, --log-verbosity N	Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values: - 0: generic output - 1: error - 2: warning - 3: info - 4: debug (default: 3) (env: LLAMA_LOG_VERBOSITY)
--log-prefix	Enable prefix in log messages (env: LLAMA_LOG_PREFIX)
--log-timestamps	Enable timestamps in log messages (env: LLAMA_LOG_TIMESTAMPS)
-ctkd, --cache-type-k-draft TYPE	KV cache data type for K for the draft model allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default: f16) (env: LLAMA_ARG_CACHE_TYPE_K_DRAFT)
-ctvd, --cache-type-v-draft TYPE	KV cache data type for V for the draft model allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default: f16) (env: LLAMA_ARG_CACHE_TYPE_V_DRAFT)

Sampling params

Argument	Explanation
--samplers SAMPLERS	samplers that will be used for generation in the order, separated by ';' (default: penalties;dry;top_n_sigma;top_k;typ_p;top_p;min_p;xtc;temperature)
-s, --seed SEED	RNG seed (default: -1, use random seed for -1)
--sampler-seq, --sampling-seq SEQUENCE	simplified sequence for samplers that will be used (default: edskypmxt)
--ignore-eos	ignore end of stream token and continue generating (implies --logit-bias EOS-inf)
--temp, --temperature N	temperature (default: 0.80)
--top-k N	top-k sampling (default: 40, 0 = disabled) (env: LLAMA_ARG_TOP_K)
--top-p N	top-p sampling (default: 0.95, 1.0 = disabled)
--min-p N	min-p sampling (default: 0.05, 0.0 = disabled)
--top-nsigma, --top-n-sigma N	top-n-sigma sampling (default: -1.00, -1.0 = disabled)
--xtc-probability N	xtc probability (default: 0.00, 0.0 = disabled)
--xtc-threshold N	xtc threshold (default: 0.10, 1.0 = disabled)
--typical, --typical-p N	locally typical sampling, parameter p (default: 1.00, 1.0 = disabled)
--repeat-last-n N	last n tokens to consider for penalize (default: 64, 0 = disabled, -1 = ctx_size)
--repeat-penalty N	penalize repeat sequence of tokens (default: 1.00, 1.0 = disabled)
--presence-penalty N	repeat alpha presence penalty (default: 0.00, 0.0 = disabled)
--frequency-penalty N	repeat alpha frequency penalty (default: 0.00, 0.0 = disabled)
--dry-multiplier N	set DRY sampling multiplier (default: 0.00, 0.0 = disabled)
--dry-base N	set DRY sampling base value (default: 1.75)
--dry-allowed-length N	set allowed length for DRY sampling (default: 2)
--dry-penalty-last-n N	set DRY penalty for the last n tokens (default: -1, 0 = disable, -1 = context size)
--dry-sequence-breaker STRING	add sequence breaker for DRY sampling, clearing out default breakers ('\n', ':', '"', '*') in the process; use "none" to not use any sequence breakers
--adaptive-target N	adaptive-p: select tokens near this probability (valid range 0.0 to 1.0; negative = disabled) (default: -1.00) (more info)
--adaptive-decay N	adaptive-p: decay rate for target adaptation over time. lower values are more reactive, higher values are more stable. (valid range 0.0 to 0.99) (default: 0.90)
--dynatemp-range N	dynamic temperature range (default: 0.00, 0.0 = disabled)
--dynatemp-exp N	dynamic temperature exponent (default: 1.00)
--mirostat N	use Mirostat sampling. Top K, Nucleus and Locally Typical samplers are ignored if used. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)
--mirostat-lr N	Mirostat learning rate, parameter eta (default: 0.10)
--mirostat-ent N	Mirostat target entropy, parameter tau (default: 5.00)
-l, --logit-bias TOKEN_ID(+/-)BIAS	modifies the likelihood of token appearing in the completion, i.e. --logit-bias 15043+1 to increase likelihood of token ' Hello', or --logit-bias 15043-1 to decrease likelihood of token ' Hello'
--grammar GRAMMAR	BNF-like grammar to constrain generations (see samples in grammars/ dir)
--grammar-file FNAME	file to read grammar from
-j, --json-schema SCHEMA	JSON schema to constrain generations (https://json-schema.org/), e.g. {} for any JSON object For schemas w/ external $refs, use --grammar + example/json_schema_to_grammar.py instead
-jf, --json-schema-file FILE	File containing a JSON schema to constrain generations (https://json-schema.org/), e.g. {} for any JSON object For schemas w/ external $refs, use --grammar + example/json_schema_to_grammar.py instead
-bs, --backend-sampling	enable backend sampling (experimental) (default: disabled) (env: LLAMA_ARG_BACKEND_SAMPLING)

CLI-specific params

Argument	Explanation
--display-prompt, --no-display-prompt	whether to print prompt at generation (default: true)
-co, --color [on|off|auto]	Colorize output to distinguish prompt and user input from generations ('on', 'off', or 'auto', default: 'auto') 'auto' enables colors when output is to a terminal
-ctxcp, --ctx-checkpoints, --swa-checkpoints N	max number of context checkpoints to create per slot (default: 32)(more info) (env: LLAMA_ARG_CTX_CHECKPOINTS)
-cpent, --checkpoint-every-n-tokens N	create a checkpoint every n tokens during prefill (processing), -1 to disable (default: 8192) (env: LLAMA_ARG_CHECKPOINT_EVERY_NT)
-cram, --cache-ram N	set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 - disable)(more info) (env: LLAMA_ARG_CACHE_RAM)
--context-shift, --no-context-shift	whether to use context shift on infinite text generation (default: disabled) (env: LLAMA_ARG_CONTEXT_SHIFT)
-sys, --system-prompt PROMPT	system prompt to use with model (if applicable, depending on chat template)
--show-timings, --no-show-timings	whether to show timing information after each response (default: true) (env: LLAMA_ARG_SHOW_TIMINGS)
-sysf, --system-prompt-file FNAME	a file containing the system prompt (default: none)
-r, --reverse-prompt PROMPT	halt generation at PROMPT, return control in interactive mode
-sp, --special	special tokens output enabled (default: false)
-cnv, --conversation, -no-cnv, --no-conversation	whether to run in conversation mode: - does not print special tokens and suffix/prefix - interactive mode is also enabled (default: auto enabled if chat template is available)
-st, --single-turn	run conversation for a single turn only, then exit when done will not be interactive if first turn is predefined with --prompt (default: false)
-mli, --multiline-input	allows you to write or paste multiple lines without ending each in ''
--warmup, --no-warmup	whether to perform warmup with an empty run (default: enabled)
-mm, --mmproj FILE	path to a multimodal projector file. see tools/mtmd/README.md note: if -hf is used, this argument can be omitted (env: LLAMA_ARG_MMPROJ)
-mmu, --mmproj-url URL	URL to a multimodal projector file. see tools/mtmd/README.md (env: LLAMA_ARG_MMPROJ_URL)
--mmproj-auto, --no-mmproj, --no-mmproj-auto	whether to use multimodal projector file (if available), useful when using -hf (default: enabled) (env: LLAMA_ARG_MMPROJ_AUTO)
--mmproj-offload, --no-mmproj-offload	whether to enable GPU offloading for multimodal projector (default: enabled) (env: LLAMA_ARG_MMPROJ_OFFLOAD)
--image, --audio FILE	path to an image or audio file. use with multimodal models, use comma-separated values for multiple files
--image-min-tokens N	minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model) (env: LLAMA_ARG_IMAGE_MIN_TOKENS)
--image-max-tokens N	maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model) (env: LLAMA_ARG_IMAGE_MAX_TOKENS)
-otd, --override-tensor-draft <tensor name pattern>=<buffer type>,...	override tensor buffer type for draft model
-cmoed, --cpu-moe-draft	keep all Mixture of Experts (MoE) weights in the CPU for the draft model (env: LLAMA_ARG_CPU_MOE_DRAFT)
-ncmoed, --n-cpu-moe-draft N	keep the Mixture of Experts (MoE) weights of the first N layers in the CPU for the draft model (env: LLAMA_ARG_N_CPU_MOE_DRAFT)
--chat-template-kwargs STRING	sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}' (env: LLAMA_CHAT_TEMPLATE_KWARGS)
--jinja, --no-jinja	whether to use jinja template engine for chat (default: enabled) (env: LLAMA_ARG_JINJA)
--reasoning-format FORMAT	controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of: - none: leaves thoughts unparsed in message.content - deepseek: puts thoughts in message.reasoning_content - deepseek-legacy: keeps <think> tags in message.content while also populating message.reasoning_content (default: auto) (env: LLAMA_ARG_THINK)
-rea, --reasoning [on|off|auto]	Use reasoning/thinking in the chat ('on', 'off', or 'auto', default: 'auto' (detect from template)) (env: LLAMA_ARG_REASONING)
--reasoning-budget N	token budget for thinking: -1 for unrestricted, 0 for immediate end, N>0 for token budget (default: -1) (env: LLAMA_ARG_THINK_BUDGET)
--reasoning-budget-message MESSAGE	message injected before the end-of-thinking tag when reasoning budget is exhausted (default: none) (env: LLAMA_ARG_THINK_BUDGET_MESSAGE)
--chat-template JINJA_TEMPLATE	set custom jinja chat template (default: template taken from model's metadata) if suffix/prefix are specified, template will be disabled only commonly used templates are accepted (unless --jinja is set before this flag): list of built-in templates: bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek-ocr, deepseek2, deepseek3, exaone-moe, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, grok-2, hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3, phi4, rwkv-world, seed_oss, smolvlm, solar-open, vicuna, vicuna-orca, yandex, zephyr (env: LLAMA_ARG_CHAT_TEMPLATE)
--chat-template-file JINJA_TEMPLATE_FILE	set custom jinja chat template file (default: template taken from model's metadata) if suffix/prefix are specified, template will be disabled only commonly used templates are accepted (unless --jinja is set before this flag): list of built-in templates: bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek-ocr, deepseek2, deepseek3, exaone-moe, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, grok-2, hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3, phi4, rwkv-world, seed_oss, smolvlm, solar-open, vicuna, vicuna-orca, yandex, zephyr (env: LLAMA_ARG_CHAT_TEMPLATE_FILE)
--skip-chat-parsing, --no-skip-chat-parsing	force a pure content parser, even if a Jinja template is specified; model will output everything in the content section, including any reasoning and/or tool calls (default: disabled) (env: LLAMA_ARG_SKIP_CHAT_PARSING)
--simple-io	use basic IO for better compatibility in subprocesses and limited consoles
--draft, --draft-n, --draft-max N	number of tokens to draft for speculative decoding (default: 16) (env: LLAMA_ARG_DRAFT_MAX)
--draft-min, --draft-n-min N	minimum number of draft tokens to use for speculative decoding (default: 0) (env: LLAMA_ARG_DRAFT_MIN)
--draft-p-min P	minimum speculative decoding probability (greedy) (default: 0.75) (env: LLAMA_ARG_DRAFT_P_MIN)
-cd, --ctx-size-draft N	size of the prompt context for the draft model (default: 0, 0 = loaded from model) (env: LLAMA_ARG_CTX_SIZE_DRAFT)
-devd, --device-draft <dev1,dev2,..>	comma-separated list of devices to use for offloading the draft model (none = don't offload) use --list-devices to see a list of available devices
-ngld, --gpu-layers-draft, --n-gpu-layers-draft N	max. number of draft model layers to store in VRAM, either an exact number, 'auto', or 'all' (default: auto) (env: LLAMA_ARG_N_GPU_LAYERS_DRAFT)
-md, --model-draft FNAME	draft model for speculative decoding (default: unused) (env: LLAMA_ARG_MODEL_DRAFT)
--spec-replace TARGET DRAFT	translate the string in TARGET into DRAFT if the draft model and main model are not compatible
--gpt-oss-20b-default	use gpt-oss-20b (note: can download weights from the internet)
--gpt-oss-120b-default	use gpt-oss-120b (note: can download weights from the internet)
--vision-gemma-4b-default	use Gemma 3 4B QAT (note: can download weights from the internet)
--vision-gemma-12b-default	use Gemma 3 12B QAT (note: can download weights from the internet)