LLAMA-SPECULATIVE(1)

👑 NAME 👑

okay so bestie, the name is llama-speculative, and the one-line summary is... also llama-speculative. That's it. That's the whole thing. No notes, no extra lore, just the name twice. iconic behavior honestly 💅✨

🦋 DESCRIPTION 🦋

This is your girl llama-speculative, and here's every single parameter she takes. Buckle up buttercup, there are so many 🎀

🌸 ----- common params ----- 🌸

• -h, --help, --usage — prints the usage and then peaces out 👋
• --version — shows you the version and the build info, no cap
• -cl, --cache-list — shows the list of models chilling in the cache
• --completion-bash — prints a source-able bash completion script for llama.cpp — you're welcome 🫶
• -t, --threads N — how many CPU threads to use during generation (default: <num_cpus>)
  • (env: LLAMA_ARG_THREADS)
• -tb, --threads-batch N — how many threads to use during batch and prompt processing (default: same as --threads)
• -C, --cpu-mask M — CPU affinity mask, and yes it's an arbitrarily long hex. Complements cpu-range (default: "")
• -Cr, --cpu-range lo-hi — the 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 this 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 — the size of the prompt context (default: 0, and 0 = loaded from the model)
  • (env: LLAMA_ARG_CTX_SIZE)
• -n, --predict, --n-predict N — how many tokens to predict (default: -1, and -1 = infinity, aka the limit does not exist 😭)
  • (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 — how many tokens to keep from the initial prompt (default: 0, and -1 = all of them)
• --swa-full — use the full-size SWA cache (default: false) — more info right here: https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055
  • (env: LLAMA_ARG_SWA_FULL)
• -fa, --flash-attn [on|off|auto] — sets the Flash Attention use — 'on', 'off', or 'auto', default: 'auto'
  • (env: LLAMA_ARG_FLASH_ATTN)
• -p, --prompt PROMPT — the prompt to start generation with; and bestie, if you want a system message, use -sys 🌟
• --perf, --no-perf — whether to enable the internal libllama performance timings (default: false) (env: LLAMA_ARG_PERF)
• -f, --file FNAME — a file containing the prompt (default: none)
• -bf, --binary-file FNAME — a binary file containing the prompt (default: none)
• -e, --escape, --no-escape — whether to process escape sequences (\n, \r, \t, \', \", \\) (default: true)
• --rope-scaling {none,linear,yarn} — RoPE frequency scaling method. Defaults to linear unless the model says otherwise (env: LLAMA_ARG_ROPE_SCALING_TYPE)
• --rope-scale N — RoPE context scaling factor, it expands the context by a factor of N (env: LLAMA_ARG_ROPE_SCALE)
• --rope-freq-base N — RoPE base frequency, the one NTK-aware scaling uses (default: loaded from the model) (env: LLAMA_ARG_ROPE_FREQ_BASE)
• --rope-freq-scale N — RoPE frequency scaling factor, expands the context by a factor of 1/N (env: LLAMA_ARG_ROPE_FREQ_SCALE)
• --yarn-orig-ctx N — YaRN: the original context size of the model (default: 0 = the model's training context size) (env: LLAMA_ARG_YARN_ORIG_CTX)
• --yarn-ext-factor N — YaRN: extrapolation mix factor (default: -1.00, and 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 — bypasses the host buffer so extra buffers can 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, we don't do that anymore 💀)
  • (env: LLAMA_ARG_DEFRAG_THOLD)
• -np, --parallel N — how many parallel sequences to decode (default: 1)
  • (env: LLAMA_ARG_N_PARALLEL)
• --mlock — DEPRECATED in favor of --load-mode: forces the system to keep the model in RAM instead of swapping or compressing it (env: LLAMA_ARG_MLOCK)
• --mmap, --no-mmap — DEPRECATED in favor of --load-mode: whether to memory-map the model. (heads up: if mmap is disabled, the load is slower but it may reduce pageouts if you're not using mlock) (env: LLAMA_ARG_MMAP)
• -dio, --direct-io, -ndio, --no-direct-io — DEPRECATED in favor of --load-mode: use DirectIO if it's available (env: LLAMA_ARG_DIO)
• -lm, --load-mode MODE — model loading mode (default: auto), and your options are:
  • auto: mmap, unless a device does not support it
  • none: no special loading mode
  • mmap: memory-map the model (if mmap is disabled, slower load but may reduce pageouts if not using mlock)
  • mlock: force the system to keep the model in RAM rather than swapping or compressing
  • mmap+mlock: mmap + force the system to keep the model in RAM rather than swapping or compressing
  • dio: use DirectIO if available
  • (env: LLAMA_ARG_LOAD_MODE)
• --numa TYPE — attempts 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 the available devices (env: LLAMA_ARG_DEVICE)
• --list-devices — prints the list of available devices and exits
• -ot, --override-tensor <tensor name pattern>=<buffer type>,... — override the tensor buffer type (env: LLAMA_ARG_OVERRIDE_TENSOR)
• -cmoe, --cpu-moe — keep all the Mixture of Experts (MoE) weights on the CPU
  • (env: LLAMA_ARG_CPU_MOE)
• -ncmoe, --n-cpu-moe N — keep the Mixture of Experts (MoE) weights of the first N layers on 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,tensor} — how to split the model across multiple GPUs, one of:
  • none: use one GPU only
  • layer (default): split layers and KV across GPUs (pipelined)
  • row: split weight across GPUs by rows (parallelized)
  • tensor: split weights and KV across GPUs (parallelized, EXPERIMENTAL) — ⚠️ that EXPERIMENTAL is doing a lot of heavy lifting, bestie
  • (env: LLAMA_ARG_SPLIT_MODE)
• -ts, --tensor-split N0,N1,N2,... — fraction of the model to offload to each GPU, a 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 so they 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, a comma-separated list of values; a single value gets broadcast across all devices, default: 1024 (env: LLAMA_ARG_FIT_TARGET)
• -fitc, --fit-ctx N — minimum ctx size that can be set by the --fit option, default: 4096
  • (env: LLAMA_ARG_FIT_CTX)
• --check-tensors — check the 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 the device (default: true)
• --lora FNAME — path to the LoRA adapter (use comma-separated values to load multiple adapters)
• --lora-scaled FNAME:SCALE,... — path to the 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] —

okay so picking up right where we left off — the Docker Hub model repository one 💅 repo is optional and defaults to ai/. quant is optional and defaults to :latest. example: gemma3 (default: unused) (env: LLAMA_ARG_DOCKER_REPO). anyway bestie, moving on 👑

• -hf, -hfr, --hf-repo <user>/<model>[:quant] — the Hugging Face model repository moment 🦋. quant is optional, case-insensitive, and defaults to Q4_K_M — or, if Q4_K_M doesn't exist in that repo, it just falls back to the first file in the repo, no cap. mmproj also gets downloaded automatically if it's available ✨. to disable that, add --no-mmproj. example: ggml-org/GLM-4.7-Flash-GGUF:Q4_K_M (default: unused) (env: LLAMA_ARG_HF_REPO)
• -hff, --hf-file FILE — Hugging Face model file. if you specify this, it will override the quant in --hf-repo 💀 (default: unused) (env: LLAMA_ARG_HF_FILE)
• -hft, --hf-token TOKEN — Hugging Face access token (default: value from the HF_TOKEN environment variable) (env: HF_TOKEN) 🔐
• --log-disable — Log disable 🙈
• --log-file FNAME — Log to file (env: LLAMA_ARG_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, which is honestly the only correct choice 🎀 (env: LLAMA_ARG_LOG_COLORS)
• -v, --verbose, --log-verbose — Set verbosity level to infinity (i.e. log all messages, useful for debugging) — it's giving main character energy, everything gets logged, nothing is hidden 🌈
• --offline — Offline mode: forces use of cache, prevents network access (env: LLAMA_ARG_OFFLINE) ✈️
• -lv, --verbosity, --log-verbosity N — Set the verbosity threshold. Messages with a higher verbosity will be ignored. the values, periodt:
  • 0: generic output
  • 1: error
  • 2: warning
  • 3: info
  • 4: trace (more info)
  • 5: debug

(default: 3) (env: LLAMA_ARG_LOG_VERBOSITY)

• --log-prefix, --no-log-prefix — Enable prefix in log messages (env: LLAMA_ARG_LOG_PREFIX)
• --log-timestamps, --no-log-timestamps — Enable timestamps in log messages (env: LLAMA_ARG_LOG_TIMESTAMPS) ⏰
• --spec-draft-type-k, -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_SPEC_DRAFT_CACHE_TYPE_K)
• --spec-draft-type-v, -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_SPEC_DRAFT_CACHE_TYPE_V)

---

✨ sampling params ✨

like, this is where the personality of your model gets decided 🎀

• --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)
• --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: 64, 0 = disable)
• --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 at all
• --adaptive-target N — adaptive-p: select tokens near this probability (valid range 0.0 to 1.0; negative = disabled) (default: -1.00) (more info: https://github.com/ggml-org/llama.cpp/pull/17927) 📖
• --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) 🧪

k just so we're clear: that backend sampling one says experimental, so if it acts up it's not being shady, it's just built different. proceed with care 🫶

---

🔮 speculative params 🔮

the draft-model section, aka the understudy of your main model 🎭 it drafts, the big model checks, everybody wins ✨

• --spec-draft-hf, -hfd, -hfrd, --hf-repo-draft <user>/<model>[:quant] — Same as --hf-repo, but for the draft model (default: unused) (env: LLAMA_ARG_SPEC_DRAFT_HF_REPO) 🦋
• --spec-draft-threads, -td, --threads-draft N — number of threads to use during generation (default: same as --threads)
• --spec-draft-threads-batch, -tbd, --threads-batch-draft N — number of threads to use during batch and prompt processing (default: same as --threads-draft)
• --spec-draft-cpu-mask, -Cd, --cpu-mask-draft M — Draft model CPU affinity mask. Complements cpu-range-draft (default: same as --cpu-mask)
• --spec-draft-cpu-range, -Crd, --cpu-range-draft lo-hi — Ranges of CPUs for affinity. Complements --cpu-mask-draft
• --spec-draft-cpu-strict, --cpu-strict-draft <0|1> — Use strict CPU placement for draft model (default: same as --cpu-strict)
• --spec-draft-prio, --prio-draft N — set draft process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: 0) ⚡
• --spec-draft-poll, --poll-draft <0|1> — Use polling to wait for draft model work (default: same as --poll)
• --spec-draft-cpu-mask-batch, -Cbd, --cpu-mask-batch-draft M — Draft model CPU affinity mask. Complements cpu-range-draft (default: same as --cpu-mask)
• --spec-draft-cpu-range-batch, -Crbd, --cpu-range-batch-draft lo-hi — Ranges of CPUs for affinity. Complements --cpu-mask-draft-batch)
• --spec-draft-cpu-strict-batch, --cpu-strict-batch-draft <0|1> — Use strict CPU placement for draft model (default: --cpu-strict-draft)
• --spec-draft-prio-batch, --prio-batch-draft N — set draft process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: 0) ⚡
• --spec-draft-poll-batch, --poll-batch-draft <0|1> — Use polling to wait for draft model work (default: --poll-draft)
• --spec-draft-override-tensor, -otd, --override-tensor-draft <tensor name pattern>=<buffer type>,... — override tensor buffer type for draft model 🧩
• --spec-draft-cpu-moe, -cmoed, --cpu-moe-draft — keep all Mixture of Experts (MoE) weights in the CPU for the draft model (env: LLAMA_ARG_SPEC_DRAFT_CPU_MOE) 🧠
• --spec-draft-n-cpu-moe, --spec-draft-ncmoe, -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_SPEC_DRAFT_N_CPU_MOE)
• --spec-draft-n-max N — number of tokens to draft for speculative decoding (default: 3) (env: LLAMA_ARG_SPEC_DRAFT_N_MAX)
• --spec-draft-n-min N — minimum number of draft tokens to use for speculative decoding (default: 0) (env: LLAMA_ARG_SPEC_DRAFT_N_MIN)
• --spec-draft-p-split, --draft-p-split P — speculative decoding split probability (default: 0.10) (env: LLAMA_ARG_SPEC_DRAFT_P_SPLIT)
• --spec-draft-p-min, --draft-p-min P — minimum speculative decoding probability (greedy) (default: 0.00) (env: LLAMA_ARG_SPEC_DRAFT_P_MIN)
• --spec-draft-backend-sampling, --no-spec-draft-backend-sampling — offload draft sampling to the backend (default: enabled) (env: LLAMA_ARG_SPEC_DRAFT_BACKEND_SAMPLING) 🧪
• --spec-draft-device, -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
• --spec-draft-ngl, -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) 🔥
• --spec-draft-model, -md, --model-draft FNAME — draft model for speculative decoding (default: unused) (env: LLAMA_ARG_SPEC_DRAFT_MODEL) 🫶
• --spec-type — comma-separated list of types of speculative decoding to use (default: none)
  • the whole menu, in this order: none, draft-simple, draft-eagle3, draft-mtp, draft-dflash, draft-dspark, ngram-simple, ngram-map-k, ngram-map-k4v, ngram-mod, ngram-cache
  • (env: LLAMA_ARG_SPEC_TYPE)
• --spec-ngram-mod-n-min N — the floor, bestie: minimum number of ngram tokens to use for ngram-based speculative decoding (default: 48)
• --spec-ngram-mod-n-max N — the ceiling this time: maximum number of ngram tokens to use for ngram-based speculative decoding (default: 64)
• --spec-ngram-mod-n-match N — how long the ngram-mod lookup gets to be, that's it, that's the whole vibe (default: 24)
• --spec-ngram-simple-size-n N — ngram size N for ngram-simple speculative decoding, which is literally the length of the lookup n-gram (default: 12)
• --spec-ngram-simple-size-m N — ngram size M for ngram-simple speculative decoding, aka the length of the draft m-gram (default: 48)
• --spec-ngram-simple-min-hits N — minimum hits for ngram-simple speculative decoding (default: 1)
• --spec-ngram-map-k-size-n N — ngram size N for ngram-map-k speculative decoding, i.e. the length of the lookup n-gram (default: 12)
• --spec-ngram-map-k-size-m N — ngram size M for ngram-map-k speculative decoding, i.e. the length of the draft m-gram (default: 48)
• --spec-ngram-map-k-min-hits N — minimum hits for ngram-map-k speculative decoding (default: 1)
• --spec-ngram-map-k4v-size-n N — ngram size N for ngram-map-k4v speculative decoding, i.e. the length of the lookup n-gram (default: 12)
• --spec-ngram-map-k4v-size-m N — ngram size M for ngram-map-k4v speculative decoding, i.e. the length of the draft m-gram (default: 48)
• --spec-ngram-map-k4v-min-hits N — minimum hits for ngram-map-k4v speculative decoding (default: 1)
• --draft, --draft-n, --draft-max N — okay so this one is gone 🚨 the argument has been removed. use --spec-draft-n-max or --spec-ngram-mod-n-max
  • (env: LLAMA_ARG_DRAFT_MAX)
• --draft-min, --draft-n-min N — same story, this one got removed too 🚨 use --spec-draft-n-min or --spec-ngram-mod-n-min
  • (env: LLAMA_ARG_DRAFT_MIN)

---

🌸 ----- example-specific params ----- 🌸

• -co, --color [on|off|auto] — Colorize output to distinguish prompt and user input from generations
  • your choices are 'on', 'off', or 'auto', default: 'auto'
  • 'auto' enables colors when output is to a terminal

---

and that's the whole page, bestie, you made it 💖 this one ships from debian, dated September 2026, and it's filed under LLAMA-SPECULATIVE(1) — go speculate responsibly, ily ✨👑🦋