Skip to content

Releases: AtomicBot-ai/atomic-llama-cpp-turboquant

TurboQuant macOS ARM64 (c419fd5)

09 Jun 16:42
@github-actions github-actions
turboquant-macos-arm64-c419fd5
c419fd5

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (c419fd5) Latest
Latest

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit c419fd5.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Assets 4
Loading

TurboQuant macOS ARM64 (9ca009a)

09 Jun 16:43
@github-actions github-actions
turboquant-macos-arm64-9ca009a
9ca009a

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (9ca009a) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit 9ca009a.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (0dbf74d)

09 Jun 16:46
@github-actions github-actions
turboquant-macos-arm64-0dbf74d
0dbf74d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (0dbf74d) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit 0dbf74d.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (0a635dc)

13 May 17:33
@github-actions github-actions
turboquant-macos-arm64-0a635dc
0a635dc
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (0a635dc) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit 0a635dc.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (e381dc9)

12 May 19:12
@github-actions github-actions
turboquant-macos-arm64-e381dc9
e381dc9
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (e381dc9) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit e381dc9.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (dcd8d77)

12 May 19:12
@github-actions github-actions
turboquant-macos-arm64-dcd8d77
dcd8d77
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (dcd8d77) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit dcd8d77.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (b1a7d71)

12 May 19:13
@github-actions github-actions
turboquant-macos-arm64-b1a7d71
b1a7d71
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (b1a7d71) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit b1a7d71.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (514e600)

12 May 20:40
@github-actions github-actions
turboquant-macos-arm64-514e600
514e600
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (514e600) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit 514e600.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (98bbdfe)

07 May 10:07
@github-actions github-actions
turboquant-macos-arm64-98bbdfe
98bbdfe
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (98bbdfe) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit 98bbdfe.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading

TurboQuant macOS ARM64 (2e81dc5)

07 May 17:12
@github-actions github-actions
turboquant-macos-arm64-2e81dc5
2e81dc5
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
TurboQuant macOS ARM64 (2e81dc5) Pre-release
Pre-release

TurboQuant KV Cache — macOS ARM64 (Metal)

Built from feature/turboquant-kv-cache branch at commit 2e81dc5.

What's included

  • llama-server with --cache-type-k turbo3 / turbo4 support
  • llama-cli, llama-bench, llama-perplexity
  • Metal backend with BF16 + embedded shader library

Usage

# Option 1: zip (notarized + stapled)
unzip llama-turboquant-macos-arm64.zip
# Option 2: tar.gz
tar -xzf llama-turboquant-macos-arm64.tar.gz

./build/bin/llama-server -m model.gguf --cache-type-k turbo3 --cache-type-v turbo3

For Atomic Chat integration

Replace the binary at:

~/Library/Application Support/Atomic Chat/data/llamacpp/backends/<version>/macos-arm64/build/bin/llama-server
Loading