llamAmpere

llamAmpere

llamAmpere is a fast version of llama.cpp (the open-source program that runs AI language models on your own computer), tuned for NVIDIA RTX 30-series "Ampere" graphics cards, especially the RTX 3090 and 3090 Ti. It runs Qwen3.8 models, including Qwen3.8-27B with its built-in MTP draft head (a small helper that guesses several words ahead so the model writes faster) and Qwen3.8 Flash-Next.

What's new in v0.6.3.8

• The DFlash2 drafter on dense Swift 1.5 27B writes about 3.4 times faster (27 -> 93 tokens/s at temperature 1.0 on an RTX 3090 Ti, 100K prompt). A mixing step in the drafter ran twice per layer; it now runs once. The big model still checks every guess, so output quality is unchanged. MTP and Flash-Next are not affected. Release notes.

What's new in v0.6.3.6

• Flash-Next runs AI4, a four-bit AI+ model file, qwen3.8-flash-next-Swift1.5-ATX-AI4 (84.97 GiB, closer to the Swift-Q8 reference than UD-IQ4_XS). Not recommended on 64 GB RAM machines unless you pin a large share of experts on the GPU and move the backup copies out of VRAM to cut RAM use.
• Fixes the Linux build failure with Clang and some other compilers (#98). Saved prompt caches are keyed by expert-routing and GGML_ settings. Release notes.

What's new in v0.6.3.5

• Flash-Next leaves more temporary card memory for long prompts on small cards. Explicit memory settings still win. Release notes and hardware limits.

What's new in v0.6.3.3

• Small cards use memory-bounded prompt passes and shorter prompt-tail chunks by default. Normally free 24 GB cards keep their previous plan.
• Fixes Windows private model mappings and MSVC atomics (#94, #93, #82). Linux launchers count physical performance cores on hybrid Intel CPUs.
• Adds CPU expert-split diagnostics and --moe-cpu-share for troubleshooting (#88). Release notes and hardware limits.

What's new in v0.6.3.2

• Fixes a Flash-Next crash when a follow-up request reuses a cached prompt with shared experts on a side stream (#88).
• Fixes Windows model loading, Windows build errors, and reads from large expert overlays (#82). Release notes.

What's new in v0.6.3.1

• Flash-Next leaves more temporary card memory on 24 GB cards and handles --parallel startup. Unsupported Flash-Next tensor split now gives a clear error.
• Small cards keep 32K prompt passes, with a 4096-token microbatch to avoid a measured prompt fallback. Adaptive prompt passes remain opt-in. Release notes.

What's new in v0.6.3

• New Flash-Next model file, qwen3.8-flash-next-Swift1.5-ATX-AI3: 80.11 GB (74.61 GiB), compared with 75.97 GB for IQ3_XXS. On an RTX 3090 with ample system RAM, this file wrote 121–125 tokens/s across coding, agentic and RAG tasks. These are observations on the new file, not a same-engine comparison with the standard file. Measured results and limits.
• The expert kernels our speed tests use are now on by default; whole-file page read-ahead when the model fits in RAM.

What's new in v0.6.1

• Faster Flash-Next: about 3% faster writing and prompt reading than v0.6 on an RTX 3090 Ti (113.15 vs 109.65 writing tokens/s, 2,751 vs 2,672 prompt tokens/s, 100K prompt; one-seed observation), and room for more experts on the card. Fixes the 12 GB startup crash. v0.6.1 release notes.

What's new in v0.6

• mb-MTP is on by default with the MTP draft head: more guessed words are kept, so writing is faster (--no-spec-mb-mtp gives exact sampling).
• Faster prompt reading on Swift 1.5 27B (+5.3% at 100K tokens) with the same output.
• AI+ model file for Swift 1.5 27B, our own weight format for Ampere and newer cards: 14.4 GB, 10.4% lower KL (a measure of drift from the full-precision model) than IQ4_XS-M. Older AI+ files no longer load.
• Qwen3.8 Flash-Next support: experts split between the card and RAM, with --kv-gpu-tokens N to keep only part of the context memory on the card.

Details, speed tables and everything older: v0.6 release notes.

Quick start

Build and run (v0.6.3.8, Qwen3.8 Flash-Next, Linux). For one RTX 30-series card with enough system RAM for the model and prompt workspace. Small-card tests used a 3090 limited to 12 GB with about 90 GiB of system RAM; native 12/16 GB cards remain unmeasured, and 64 GB of system RAM is not a fit promise. Small cards use memory-bounded prompt passes; see the hardware limits. The launcher keeps the tested --fit off setting; its own card planner still chooses the memory plan and keeps at least 5 GiB of RAM free. Automatic --fit on has not been measured on this file. Needs the CUDA 12 or newer toolkit (nvcc), CMake, git, a C++ compiler, the hf download tool (pip install -U huggingface_hub) and 81.63 GB for the model and drafter, plus space for the build, prompt scratch and saved prompts. The launcher uses a 5 GiB free-RAM floor. This one paste clones or updates llamAmpere at v0.6.3.8, builds llama-server, downloads the model and its drafter and starts the server:

if [ -d llamAmpere ]; then
  git -C llamAmpere fetch --tags --force && git -C llamAmpere checkout v0.6.3.8
else
  git clone -b v0.6.3.8 https://github.com/JakeATX/llamAmpere.git
fi && cd llamAmpere && \
cmake -S . -B build-sm86 -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=86 -DLLAMA_BUILD_BORINGSSL=ON && \
cmake --build build-sm86 -j8 --target llama-server && \
hf download jakeatx/qwen3.8-flash-next-Swift1.5-ATX-AI3 --include '*.gguf' --local-dir models/flash-next && \
hf download jakeatx/Swift-1.5-Qwen3.8-Flash-Next-MTP-Drafter-GGUF mtp-Swift-Qwen3.8-Flash-Next-GSQ-RCO-Q2S-B.gguf --local-dir models/flash-next && \
LLAMA_SERVER_BIN=build-sm86/bin/llama-server \
FLASH_NEXT_DRAFTER=models/flash-next/mtp-Swift-Qwen3.8-Flash-Next-GSQ-RCO-Q2S-B.gguf \
scripts/flash-next-server.sh -m models/flash-next/qwen3.8-flash-next-Swift1.5-ATX-AI3-00001-of-00002.gguf

To start it again later, run the last three lines from the llamAmpere folder. The server listens on http://127.0.0.1:8080 (OpenAI-compatible API).

Build and run (v0.6.3.8, Swift 1.5 27B at 2.3 bpw, 200K context, one 24 GB RTX 30-series card, Linux). Needs the CUDA 12 or newer toolkit (nvcc), CMake, git and a C++ compiler. The model (about 9.1 GB) downloads on first start. This one paste clones or updates llamAmpere at v0.6.3.8, builds llama-server and starts it:

if [ -d llamAmpere ]; then
  git -C llamAmpere fetch --tags --force && git -C llamAmpere checkout v0.6.3.8
else
  git clone -b v0.6.3.8 https://github.com/JakeATX/llamAmpere.git
fi && cd llamAmpere && \
cmake -S . -B build-sm86 -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=86 -DLLAMA_BUILD_BORINGSSL=ON && \
cmake --build build-sm86 -j8 --target llama-server && \
./build-sm86/bin/llama-server -hf jakeatx/qwen3.8-27b-Swift1.5-Uncensored-ATX-AI2 \
  -c 204800 -ngl 99 -fa on -b 4096 -ub 1024 --parallel 1 --jinja --no-context-shift \
  -ctk sjkvarn3 -ctv sjkvarn2 --sjkvarn-body-type auto \
  --spec-type draft-mtp-adaptive --spec-draft-n-min-adaptive 3 --spec-draft-n-max 4 \
  --spec-draft-p-min 0 --spec-mb-mtp

Commands for 12 and 10 GB cards (not yet run on this model) are in the v0.6.2 release notes.

The server listens on http://127.0.0.1:8080 (OpenAI-compatible API). Add --no-spec-mb-mtp for exact drafting. To use the IQ4_XS-M file (15.6 GB, also runs in mainline llama.cpp) instead, use --hf-repo jakeatx/ATX-Swift-1.5-Qwen3.8-27B-Uncensored-IQ4_XS-M-GGUF --hf-file ATX-Swift-1.5-Qwen3.8-27B-Uncensored-IQ4_XS-M.gguf.

Headline results

Numbers for this release (Swift 1.5 27B, v0.6 against v0.5) are in the v0.6 release notes.

Links

• Release notes: v0.6.3.8, v0.6.3.6, v0.6.3.5, v0.6.3.3, v0.6.3.2, v0.6.3.1, v0.6.3, v0.6.2, v0.6.1, v0.6, v0.5, v0.4, v0.3.1; recommended settings for each card size: v0.5 RECOMMENDED.md
• Models: huggingface.co/jakeatx, Qwen3.8 Flash-Next collection
• Background: QWEN_AMPERE.md, write-up, flags in docs/speculative.md and docs/KV-cache-quantization.md
• SJ-KVaRN paper: paper, codec JakeATX/sj-kvarn-codec (MIT)
• Upstream llama.cpp README (quick start, backends, docs index): docs/llama.cpp-upstream-README.md

License and credits

llamAmpere is MIT licensed (see LICENSE). It is a fork of llama.cpp by the ggml authors and includes work from TheTom's TurboQuant fork. It is the successor of llama-cpp-qwen-ampere. Contributing: CONTRIBUTING.md.

Third-party libraries (from upstream llama.cpp):

• yhirose/cpp-httplib - Single-header HTTP server, used by llama-server - MIT license
• nothings/stb - Single-header image format decoder, used by multimodal subsystem - Public domain
• nlohmann/json - Single-header JSON library, used by various tools/examples - MIT License
• mackron/miniaudio - Single-header audio format decoder, used by multimodal subsystem - Public domain
• sheredom/subprocess.h - Single-header process launching solution for C and C++ - Public domain