docs / benchmarks / llm

Benchmarks index
  1. Overview
  1. Exemptions
  2. Methodology

aot

  1. Overview
  2. Components

codec

  1. Overview
  2. Base32
  3. Base64
  4. Deflate (dev.cajeta.codec)

codec / csv

  1. CSV

codec / json

  1. JSON

collection

  1. Overview
  2. ArrayList
  3. BPlusTree
  4. Cache
  5. Collectors
  6. HashMap
  7. HashSet
  8. Heap
  9. ImmutableList
  10. ImmutableMap
  11. ImmutableSet
  12. LinkedList
  13. RedBlackTree
  14. Sort

collection / ltm

  1. LtmBPlusTree

concurrent

  1. Overview
  2. AtomicInt32
  3. AtomicInt64
  4. Channel
  5. Fiber
  6. FiberLocal
  7. Lock
  8. Mutex
  9. RwLock
  10. Semaphore
  11. Tasks

gfx

  1. Overview
  2. Texture2D

hash

  1. Overview
  2. DefaultHasher
  3. Hash
  4. SipHash
  5. XXHash3

http

  1. Overview
  2. Client
  3. Server
  4. Server-sent events
  5. Start-up and footprint
  6. TLS
  7. WebSocket

io

  1. Overview
  2. Buffer

io / file

  1. Directory walk
  2. File
  3. FileInfo
  4. FileReader
  5. FileWriter
  6. Path
  7. Watcher

io / net

  1. BufferPool
  2. ByteBuffer
  3. Server
  4. TcpListener
  5. TcpStream
  6. UdpSocket

io / net / uri

  1. Uri
  2. UriBuilder

lang

  1. Overview
  2. Allocation and ownership
  3. Calls and dispatch
  4. Exceptions
  5. Guid
  6. Loops
  7. Math and SIMD
  8. Optional
  9. Pair
  10. Slice
  11. String
  12. StringBuilder
  13. Whole programs: the Benchmarks Game

lang / stream

  1. ArrayStream
  2. Stream

llm

  1. Overview
  2. Decode
  3. Kernel parity
  4. Load and first token
  5. Long context
  6. Memory
  7. Prefill

math

  1. Overview
  2. Ray
  3. Rotation
  4. Tensor
  5. Transform

math / fft

  1. Fft

math / linalg

  1. LinAlg

math / npio

  1. Npy

math / poly

  1. Poly

math / random

  1. Generator

math / stats

  1. Stats

ml

  1. Overview
  2. Classical models
  3. Neural models
  4. XGBoost

nucleo

  1. Overview
  2. Column
  3. Fuse
  4. Table
  5. Tape
  6. Transforms

primavera

  1. Overview
  2. Build time
  3. Dependency injection at scale
  4. REST endpoint
  5. Start-up and footprint
  6. Templated page

process

  1. Overview
  2. Command
  3. Process

reflect

  1. Overview
  2. Class

search

  1. Overview

search / distance

  1. Distance

search / fuzzy

  1. Matcher

search / ngram

  1. Index

time

  1. Overview
  2. Clock
  3. DateTimeFormatter
  4. Duration
  5. Instant
  6. LocalDate
  7. LocalDateTime
  8. LocalTime
  9. ZonedDateTime

toolchain

  1. Overview
  2. Binary size
  3. Build tool
  4. Compile time
  5. Debugger
  6. Notebook kernel start-up
  7. Start-up

toolchain / kernel-startup

  1. Overview
  2. Where cold-start time goes

wire

  1. Overview
  2. CompressStream
  3. Encoder
  4. SchemaEncoder

xpu

  1. Overview
  2. Device
  3. KernelBuffer
  4. KernelStream
  5. KernelTimer

xpu / mesh

  1. MeshSimplifier
Machine
no runs yet

Load and first token

dev.cajeta.llm — time to load a model from safetensors and from GGUF, and time to the first generated token.

Benchmarks

idworkloadagainstcheck
llm/load-ggufload Llama-3.1-8B Q4_K_M from GGUF to ready; variants per quantizationllama.cpp (CUDA on Phoenix; HIP and Vulkan on Proton), commit recorded on the rowfirst token matches
llm/load-safetensorsload Llama-3.1-8B from safetensorsllama.cpp cannot; the row is cajeta-llm alonefirst token matches
llm/ttfttime to first token after a 512-token prompt, warmllama.cpp (CUDA on Phoenix; HIP and Vulkan on Proton), commit recorded on the rowtoken matches

Results

One chart per benchmark, for the machine selected at the top of the page. Languages are the bars, best first; Cajeta’s bar is in color and the competitors’ are gray. A skipped competitor keeps its row with the reason in place of a bar. A benchmark with no row on the selected machine says so and shows nothing else.

llm/load-gguf

Not yet measured on Proton.
llm/load-safetensors

Not yet measured on Proton.
llm/ttft

Not yet measured on Proton.

Reproduce

cd bench
./bench.sh --bench load-gguf               # Cajeta
./bench.sh --bench load-gguf --competitors # every pinned competitor

Every row records the compiler and competitor versions, flags, machine, OS and driver; METHODOLOGY states the rules a number must satisfy before it is published.

See also

  • Benchmark source: cajeta-llm/bench/
  • Library: cajeta-llm

Source: bench/llm/Load.md · 1 min read · 218 words