Experiment Complete Published
Rapid-MLX 1.0.2 on M5 Max · 64 GiB, Metal
LFM2.5 1.2B Instruct as mlx-affine-4bit-g64 (4-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 12 Nov 2026, 21:43 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.
Experiment id s3-lfm2.5-1.2b-4-bit-rapid-mlx-256
Summary
Over 6 valid trials of 6 attempted (6 planned), computed from the raw trials below.
| Metric | Median | Range | Mean ± SD | Quartiles |
|---|---|---|---|---|
| Decode speed tok/s, higher is better | 575.8 | 523.4–582.9 | 567.0 ± 22.0 | 568.8–577.3 |
| Time to first token ms, lower is better | 34.8 | 34.2–36.6 | 35.0 ± 0.9 | 34.3–35.4 |
| Peak memory GiB, lower is better | 1.12 | 1.11–1.14 | 1.12 ± 0.02 | 1.11–1.14 |
| Prefill speed tok/s, higher is better | 7,493 | 7,106–7,622 | 7,443 ± 202.9 | 7,349–7,606 |
Trials, metric by metric
The line runs from the lowest to the highest valid trial, the dot is the median and each tick is one trial.
Every trial
Raw token counts and durations, with the speeds computed from them. Invalid trials stay in the record with their reason; they are left out of the summary, never silently dropped.
| Trial | Time to first token ms | Prefill tok/s | Decode tok/s | Peak memory GiB | Thermal | Note |
|---|---|---|---|---|---|---|
| 1 | 35.1 | 7,419256 tok in 34.5 ms, engine | 566.6127 tok in 224 ms, engine | 1.11 | nominal → nominal | |
| 2 | 34.4 | 7,566256 tok in 33.8 ms, engine | 575.9127 tok in 221 ms, engine | 1.11 | nominal → nominal | |
| 3 | 35.5 | 7,326256 tok in 34.9 ms, engine | 575.7127 tok in 221 ms, engine | 1.12 | nominal → nominal | |
| 4 | 36.6 | 7,106256 tok in 36.0 ms, engine | 577.7127 tok in 220 ms, engine | 1.14 | nominal → nominal | |
| 5 | 34.2 | 7,622256 tok in 33.6 ms, engine | 582.9127 tok in 218 ms, engine | 1.14 | nominal → nominal | |
| 6 | 34.3 | 7,619256 tok in 33.6 ms, engine | 523.4127 tok in 243 ms, engine | 1.11 | nominal → nominal |
Caveats
- Publisher cards identify the base model but do not always pin the exact export source checkpoint revision.
- Engines may differ in quantization scheme, effective KV cache precision, kernels, and activations.
Configuration
Device
- Device
- Apple Mac17,6
- Cohort
- Apple silicon Macs (desktop)
- SoC
- Apple M5 Max
- CPU
- 18-core Apple CPU
- GPU
- Not recorded
- NPU
- Not recorded
- RAM
- 64.00 GiB
- OS
- macOS 27.2.0 (26B123)
- Kernel
- 27.2.0
- Power
- mains
- Low power mode
- No
- Performance mode
- Not recorded
Engine
- Engine
- Rapid-MLX
- Maintainer
- Rapid-MLX contributors
- License
- Apache-2.0, open source
- Version
- 1.0.2
- Commit
- f1aa011aa91bb38140ed3fb68f6267b77447ee0f
- Binary SHA-256
- d5c9b638732cda0b2e2a816aa85cc1780e0a3c1b690bb23c8d9b4d3ac81a527c
- Built from
- package
- Build flags
- None
- Backend
- Metal
- Threads
- Not recorded
- Interface
- python-worker
- Settings in effect
- backend=Device(gpu, 0) model_source=artifact folder context_length=4096 batch_size=1 max_num_seqs=1 max_concurrent_requests=1 prefill_batch_size=1 completion_batch_size=1 prefill_step_size=2048 prefix_cache=false disk_caches=false speculative=false spec_decode=none suffix_decoding=false response_cache_entries=0 pflash=off kv_cache_dtype=bf16 kv_quantized=false admission_window_ms=0 stream_interval=1 gpu_memory_utilization=0.9 greedy=true temperature=0 sampler=argmax trust_remote_code=false telemetry=false weight_bits=4 weight_group_size=64
Model and weights
- Base model
- LFM2.5 1.2B Instruct (LFM2.5, 1.2B)
- Upstream
- LiquidAI/LFM2.5-1.2B-Instruct@b9d816ab510f9a28dca37cb182e9da8b0226e13c
- Weights
- LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit@7ccafdb04c36936f4f1c4685198c6c9a40275932
- Format
- safetensors
- File 1
- README.md · 2,220 bytes · sha256 116777890bc3b8cdb8cee2356a3f7f30902b40d9fcabbff5d0914a2c3812618b
- File 2
- chat_template.jinja · 1,836 bytes · sha256 3acb41f339d069a43037e6b9a9715cbeece8874eb25a7cabf1a33903d7724d6d
- File 3
- config.json · 1,572 bytes · sha256 3201758c1b68e92a8102583626b0d76f70ff4c6fc2e2b99d32e96cdbe6788cea
- File 4
- generation_config.json · 132 bytes · sha256 5ffd97da1dec4308543894569662d96e923ed01f7a9d8c7ff5aea7f800738cbd
- File 5
- model.safetensors · 628.0 MiB · sha256 d837f243744bbdbe7dd032f90b482a1c45d5b6035b25c1d7804d0f4c74b5c004
- File 6
- model.safetensors.index.json · 23,414 bytes · sha256 3074009e9be56358bf8edc25354572cbca2b5a625e02f8a2c2789a656f51f5a1
- File 7
- special_tokens_map.json · 434 bytes · sha256 742aefe2b7dec496e8caffdba03a75d0c1a9925d53bd3f3e0d388c96b591b6f4
- File 8
- tokenizer.json · 4.5 MiB · sha256 df1d8d5ec5d091b460562ffd545e4a5e91d17d4a0db7ebe733be34ed374377bd
- File 9
- tokenizer_config.json · 92,225 bytes · sha256 2a52ec012d3df831ba434b081bef3726a6ee22501f062ad8353c557a0cfa0d01
- Quantization
- mlx-affine-4bit-g64 (4-bit)
- Weight bits
- 4
- Group size
- 64
- KV cache
- model-dtype
- Conversion
- Published upstream by LiquidAI
- Conversion command
- Not recorded
Workload
- Workload
- Archive 256 input / 128 output
- Prompt
- 256 tokens, from prompts/source.txt
- Prompt SHA-256
- c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
- Chat template
- ba551d58630afa3190b1be3602e28301f3d2e9bbac978dfc49d6d825171648b6
- Output
- 128 tokens, ignoring end of sequence
- Context length
- 4,096
- Batch size
- 1
- Sampling
- Greedy
- Timing
- One streamed request per trial
- Warmup
- 2 runs, not counted
- Trials planned
- 6
- Cooldown
- 15 s between trials
Conditions
- Ambient
- Not recorded
- Thermal at start
- nominal
- Thermal at end
- nominal
- Thermal gate
- macOS thermal state nominal
- Throttling detected
- No
Provenance
- Measured by
- Glenn Sonna, Xybrid
- Operator affiliation
- Xybrid
- Run at
- 12 Nov 2026, 21:43 UTC
- Harness
- xybrid-bench 0.4.0 (a101f5a635e0541dbb6a1f784441a4634584f414)
- Methodology
- v0.6
- Publication
- published
- Published
- 16 Nov 2026, 10:23 UTC
- Reviewed by
- Glenn Sonna
Output check
- Result
- Failed
- Method
- sanity-v1-bf16-reference
- Reference
- checks/sanity-v1.json
- Reference SHA-256
- a702dee079525ae0ec90465b1c9e26052c99cb3e1c53e83dea05be4c194fc7ca
- Required passing checks
- 11
- Check arithmetic
- Failed · sha256 7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451
- Check capital
- Passed · sha256 5dd272b4f316b776a7b8e3d0894b37e1e42be3d5d3b204b8a5836cc50597a6b1
- Check opposite
- Passed · sha256 f151cd9e12c8994edfa316e4624f956bc68460454869177f287146f8cc956a12
- Check weekday
- Passed · sha256 7d8af1de1262f150187d5938bf649d6c35726970685f916d1ec6392a801b9762
- Check color
- Failed · sha256 19dd83f117525b931fccdafe808aaa6939af792ee549f359eff13fac0d622f5d
- Check sort
- Passed · sha256 a386b3c9b4b4786df5bb6474bab0a62b8476e2f3f9c8a6433aca40152840f6b7
- Check animal
- Passed · sha256 4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a
- Check word
- Passed · sha256 3b635d3b4437e023e72a9df26201b6ab51285b376446446ebb379121994550f6
- Check copy
- Passed · sha256 d61e6890d0e3571b0c7693612d41f8d059a1fcdef4ba959c0af4144541d41907
- Check needle-start
- Passed · sha256 8b9af2e5b8b4cfddb87d171997b95c471f8d68a68e30fb5177abeb3332372edd
- Check needle-end
- Passed · sha256 e6589c736af32f81bf239c5eda6de41959122ccc1d05463b75e0eb0c70fc831c
- Check continuation-128
- Passed · sha256 fe1fdf5d49caa68c1ef2f8a341413cb2c3826023aef1113c6c289dcd86193b32
- Detail
- 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.
Reproduce it
pnpm bench run --plan plans/s3-lfm2.5-1.2b-4-bit.json
Three palindromic blocks per quantization class and workload; load, two warmups, one trial, unload per turn.
Raw data
- This record, as committed JSON, schema v0.3.0
- Complete finalized session evidence raw ·
sha256 83ed1948cfa3…