Experiment Complete Published
Ollama 0.40.13 on M5 Max · 64 GiB, Metal
LFM2.5 2.6B as Q8_0 (8-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 12 Nov 2026, 22:43 UTC by Glenn Sonna, Xybrid.
Eligible for ranking when the objective's required metrics are measured and this configuration is selected.Approximate comparison: The experiments use different effective KV cache precision: litert-lm default, f16, model-dtype. The experiments here use different 8-bit schemes: litert-int8, Q8_0, mlx-affine-8bit-g64.
Experiment id s3-lfm2.5-2.6b-8-bit-ollama-2048
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 | 153.6 | 153.3–153.9 | 153.6 ± 0.2 | 153.5–153.7 |
| Time to first token ms, lower is better | 283 | 283–284 | 283 ± 0.7 | 283–284 |
| Peak memory GiB, lower is better | 2.97 | 2.97–2.97 | 2.97 ± 0.00 | 2.97–2.97 |
| Prefill speed tok/s, higher is better | 7,306 | 7,275–7,317 | 7,300 ± 16.1 | 7,290–7,310 |
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 | 283 | 7,3092,048 tok in 280 ms, engine | 153.3127 tok in 828 ms, engine | 2.97 | nominal → nominal | |
| 2 | 283 | 7,3102,048 tok in 280 ms, engine | 153.6127 tok in 827 ms, engine | 2.97 | nominal → nominal | |
| 3 | 283 | 7,3032,048 tok in 280 ms, engine | 153.7127 tok in 826 ms, engine | 2.97 | nominal → nominal | |
| 4 | 284 | 7,2862,048 tok in 281 ms, engine | 153.5127 tok in 827 ms, engine | 2.97 | nominal → nominal | |
| 5 | 284 | 7,2752,048 tok in 281 ms, engine | 153.5127 tok in 827 ms, engine | 2.97 | nominal → nominal | |
| 6 | 283 | 7,3172,048 tok in 280 ms, engine | 153.9127 tok in 825 ms, engine | 2.97 | 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
- Ollama
- Maintainer
- Ollama
- License
- MIT, open source
- Version
- 0.40.13
- Commit
- Not recorded
- Binary SHA-256
- 270089e59e1d411ac4d0987154b4e95f48b29a81c9d274833c6b766d6df88300
- Built from
- release
- Build flags
- None
- Backend
- Metal
- Threads
- Not recorded
- Interface
- http-server
- Settings in effect
- backend=metal model=xybrid-1e22128dfa128bdf blob=sha256-1e22128dfa128bdfb684da167e74e072d0a056baa7d06d9f280291e2839b0fc9 offloaded_layers=31 bos_stripped=true llama_server.host=127.0.0.1 llama_server.no-webui=true llama_server.offline=true llama_server.c=4096 llama_server.np=1 llama_server.log-verbosity=4 llama_server.no-log-prefix=true llama_server.no-log-timestamps=true llama_server.cache-type-k=f16 llama_server.cache-type-v=f16 llama_server.flash-attn=on llama_server.b=512 llama_server.ub=512 llama_server.context-shift=true llama_server.keep=4 env.OLLAMA_KEEP_ALIVE=-1 env.OLLAMA_FLASH_ATTENTION=1 env.OLLAMA_KV_CACHE_TYPE=f16 env.OLLAMA_NOHISTORY=1 env.OLLAMA_NUM_PARALLEL=1 env.OLLAMA_MAX_LOADED_MODELS=1 env.LLAMA_ARG_CACHE_RAM=0
Model and weights
- Base model
- LFM2.5 2.6B (LFM2.5, 2.6B)
- Upstream
- LiquidAI/LFM2.5-2.6B@7141b56cd4650af95c7c7b86983443aed050c96a
- Weights
- LiquidAI/LFM2.5-2.6B-GGUF@e7caca5d835a3901a8e0d63e94009429bafafdfc
- Format
- gguf
- File 1
- LFM2.5-2.6B-Q8_0.gguf · 2.68 GiB · sha256 1e22128dfa128bdfb684da167e74e072d0a056baa7d06d9f280291e2839b0fc9
- File 2
- README.md · 3,068 bytes · sha256 d08b79260b3998e96792777085e4175b730667568f3a953ad4ac9099cfa27056
- Quantization
- Q8_0 (8-bit)
- Weight bits
- 8
- Group size
- 32
- KV cache
- f16
- Conversion
- Published upstream by LiquidAI
- Conversion command
- Not recorded
Workload
- Workload
- Archive 2048 input / 128 output
- Prompt
- 2,048 tokens, from prompts/source.txt
- Prompt SHA-256
- c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
- Chat template
- ea663864491de7ade391839479860ca95541f892f72665c73251fbd4643b1bef
- 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, 22:43 UTC
- Harness
- xybrid-bench 0.4.0 (777cb3d9fecaa7cc1a30694d98492c33dbc6d693)
- Methodology
- v0.6
- Publication
- published
- Published
- 16 Nov 2026, 10:23 UTC
- Reviewed by
- Glenn Sonna
Output check
- Result
- Passed
- Method
- sanity-v1-bf16-reference
- Reference
- checks/sanity-v1.json
- Reference SHA-256
- a702dee079525ae0ec90465b1c9e26052c99cb3e1c53e83dea05be4c194fc7ca
- Required passing checks
- 8
- Check arithmetic
- Passed · sha256 68ce25cb2c4b530f85434cd352428b022149c641163300e566f4f9ee9d789bcf
- Check capital
- Passed · sha256 b1098d691672b55e98767ac84c6d8375f7bcc0d78154c861ea70ac2ff66e0ba7
- Check opposite
- Passed · sha256 7c90b06eef25984adf77ec226311829bbc1065a033e9ad6b26d9bd0dfdc65f95
- Check weekday
- Passed · sha256 03db656ee680fb1053be9c98631722488bb10269075159dbae5b000f0359dae2
- Check color
- Failed · sha256 a4849893c59e4aa15ff645cadd4cce0fbd882097352a75d8e6f23619578a73c6
- Check sort
- Failed · sha256 6904619ddb316a20bc1220a9088da9a4181f1f16766b6fdd188defd9cddc4c75
- Check animal
- Passed · sha256 3e9114b6df29561433c18b3a6abce2c635fbd8e9ff25b5fcee93149bfea52859
- Check word
- Passed · sha256 d1bf31457072aaa4c116ea5819a644456232fdd87b15203d3eafdd5e541f4e61
- Check copy
- Passed · sha256 d8c711dfa5fef68d1d0f86320daeca065b91bc8d0dbcea210f8b9ef80eefc6c2
- Check needle-start
- Passed · sha256 56a69645d0ff053b3b7001c224f07a374bf963a22c9fa4706dda5e56e3616870
- Check needle-end
- Failed · sha256 0f97f855a97e7b397b129f50bdc8840f19221695dc7199f2c62ea9875b504298
- Check continuation-128
- Passed · sha256 35b435d7f1c75bb05c07d58cad000525a1d62d6dbe7fd00ae7416953dfa26286
- Detail
- 9/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end.
Reproduce it
pnpm bench run --plan plans/s3-lfm2.5-2.6b-8-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 92db4b58d893…