{"name":"Muse-Glimmer 30B","arena":{"id":"muse-glimmer-30b-bf16","name":"Muse-Glimmer 30B","vram":60,"params":30,"vendor":"meta","quality":{"coding":null,"science":{"bench":"GPQA-Diamond","value":83.5},"knowledge":null},"contextK":128,"baseModelId":"muse-glimmer-30b"},"notes":"Model-ID: meta-models/Muse-Glimmer-30B. Container: vllm/vllm-openai:muse-glimmer. llama-benchy 0.4.0. Bronrun: 2026-08-12T03:05:02+02:00. KV-cache auto; max_model_len 131072; gpu_memory_utilization 0,9. Prefix caching uit; async scheduling uit. Extra serverflags: --max-num-batched-tokens 8192 --max-num-seqs 256 --generation-config auto --enable-auto-tool-choice --tool-call-parser muse_glimmer --reasoning-parser muse_glimmer. 11 van de 11 tests hebben een meting die volgens de huidige Arena-regels meetelt. De sanity-check is geslaagd. Dit is een controle op een kort gegenereerd antwoord, geen inhoudelijke evaluatie van de benchmarktaken.","order":160,"engine":"vLLM v0.26.1rc1.dev608+g99a10304d","verdict":"Gemeten op 2026-08-12 met vLLM v0.26.1rc1.dev608+g99a10304d. In de chattest met tien gelijktijdige verzoeken haalt dit profiel 4,07 tokens/s per gebruiker, met gemiddeld 4,93 seconden tot het eerste token. Bij 25k context stijgt die gemiddelde wachttijd naar 88,62 seconden. Deze runs meten snelheid en wachttijd, niet de kwaliteit van de antwoorden.","hardware":"DGX Spark, NVIDIA GB10, 128 GB unified memory","modelUrl":"https://huggingface.co/meta-models/Muse-Glimmer-30B","provider":"meta-models","precision":"BF16","parameters":"30B","provenance":{"modelId":"meta-models/Muse-Glimmer-30B","runPath":"results/muse-glimmer/muse-glimmer-30b/bf16","validity":{"tests":{"01-chat":"complete","02-rag-8k":"complete","08-sharegpt":"complete","09-reasoning":"complete","04-multi-turn":"complete","11-rate-sweep":"complete","03-long-output":"complete","05-big-context":"complete","10-monday-peak":"complete","07-office-baseline":"complete","06-concurrency-stress":"complete"},"sanity":"passed"},"sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","servedName":"muse-glimmer-30b-bf16","generatedAt":"2026-08-12T03:05:02+02:00","runRevision":"a948cec23b054c62fef595bad3cdb284066922ac","vllmVersion":"0.26.1rc1.dev608+g99a10304d","suiteVersion":"2026-08","repositoryUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks","contractVersion":1,"contractRevision":"a948cec23b054c62fef595bad3cdb284066922ac","commandProvenance":"reconstructed_from_raw_artifacts","llamaBenchyVersion":"0.4.0"},"architecture":"Dense","measuredContextK":128,"benchmarkResults":[{"id":"muse-glimmer-30b-bf16-chat-1k","date":"2026-08-12","runs":3,"metrics":{"ttfrSec":{"mean":4.927,"stddev":1.874},"decodeTokensPerSecondTotal":{"mean":40.61,"stddev":0.01},"prefillTokensPerSecondTotal":{"mean":1317.97,"stddev":64.5},"decodeTokensPerSecondPerUser":{"mean":4.07,"stddev":0.03}},"sourceRun":"Test 01","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","workloadId":"chat-1k","sourceLabel":"meta-models/Muse-Glimmer-30B bf16 op de DGX Spark","sourceStatus":"complete","sourceTestId":"01-chat","prefixCaching":false},{"id":"muse-glimmer-30b-bf16-rag-8k","date":"2026-08-12","runs":3,"metrics":{"ttfrSec":{"mean":28.816,"stddev":15.05},"decodeTokensPerSecondTotal":{"mean":31.98,"stddev":0.79},"prefillTokensPerSecondTotal":{"mean":1475.69,"stddev":7.45},"decodeTokensPerSecondPerUser":{"mean":3.71,"stddev":0.26}},"sourceRun":"Test 02","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","workloadId":"rag-8k","sourceLabel":"meta-models/Muse-Glimmer-30B bf16 op de DGX Spark","sourceStatus":"complete","sourceTestId":"02-rag-8k","prefixCaching":false},{"id":"muse-glimmer-30b-bf16-long-output-agents","date":"2026-08-12","runs":3,"metrics":{"ttfrSec":{"mean":1.598,"stddev":0.424},"decodeTokensPerSecondTotal":{"mean":34.49,"stddev":3.58},"prefillTokensPerSecondTotal":{"mean":881.37,"stddev":42.81},"decodeTokensPerSecondPerUser":{"mean":4.09,"stddev":0.03}},"sourceRun":"Test 03","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","workloadId":"long-output-agents","sourceLabel":"meta-models/Muse-Glimmer-30B bf16 op de DGX Spark","sourceStatus":"complete","sourceTestId":"03-long-output","prefixCaching":false},{"id":"muse-glimmer-30b-bf16-multi-turn-office","date":"2026-08-12","runs":3,"metrics":{"ttfrSec":{"mean":8.327,"stddev":3.592},"decodeTokensPerSecondTotal":{"mean":39.74,"stddev":0.14},"prefillTokensPerSecondTotal":{"mean":1441.48,"stddev":5.58},"decodeTokensPerSecondPerUser":{"mean":4,"stddev":0.04}},"sourceRun":"Test 04","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","workloadId":"multi-turn-office","sourceLabel":"meta-models/Muse-Glimmer-30B bf16 op de DGX Spark","sourceStatus":"complete","sourceTestId":"04-multi-turn","prefixCaching":false},{"id":"muse-glimmer-30b-bf16-large-context-25k","date":"2026-08-12","runs":3,"metrics":{"ttfrSec":{"mean":88.62,"stddev":44.671},"decodeTokensPerSecondTotal":{"mean":13.11,"stddev":0.02},"prefillTokensPerSecondTotal":{"mean":1435,"stddev":0.95},"decodeTokensPerSecondPerUser":{"mean":2.43,"stddev":0.88}},"sourceRun":"Test 05","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","workloadId":"large-context-25k","sourceLabel":"meta-models/Muse-Glimmer-30B bf16 op de DGX Spark","sourceStatus":"complete","sourceTestId":"05-big-context","prefixCaching":false},{"id":"muse-glimmer-30b-bf16-concurrency-stress-25k","date":"2026-08-12","runs":3,"metrics":{"ttfrSec":{"mean":167.973,"stddev":91.474},"decodeTokensPerSecondTotal":{"mean":13.77,"stddev":0.04},"prefillTokensPerSecondTotal":{"mean":1412.05,"stddev":0.81},"decodeTokensPerSecondPerUser":{"mean":1.54,"stddev":0.82}},"sourceRun":"Test 06","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","workloadId":"concurrency-stress-25k","sourceLabel":"meta-models/Muse-Glimmer-30B bf16 op de DGX Spark","sourceStatus":"complete","sourceTestId":"06-concurrency-stress","prefixCaching":false}],"openLoopResults":[{"id":"muse-glimmer-30b-bf16-office-random-4k","date":"2026-08-12","metrics":{"e2eMs":{"p50":795338.49,"p90":1116660.66,"p95":1203860.5,"p99":1274191.32,"mean":757257.76},"tpotMs":{"p50":1663.08,"p90":2837.17,"p95":3265.51,"p99":3837.32,"mean":1815.43},"ttftMs":{"p50":17039.38,"p90":30607.93,"p95":38336.92,"p99":43651.44,"mean":18434.64}},"sourceRun":"Test 07","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","scenarioId":"office-random-4k","achievedRps":0.143,"sourceStatus":"complete","sourceTestId":"07-office-baseline","configuredRps":0.3,"prefixCaching":false,"totalRequests":200,"successfulRequests":200,"totalTokenThroughput":658.2,"peakConcurrentRequests":190},{"id":"muse-glimmer-30b-bf16-sharegpt-replay","date":"2026-08-12","metrics":{"e2eMs":{"p50":33472.09,"p90":121738.98,"p95":156322.09,"p99":199205.34,"mean":51061},"tpotMs":{"p50":252.54,"p90":261.54,"p95":268.81,"p99":296.77,"mean":252.3},"ttftMs":{"p50":762.76,"p90":1064.3,"p95":1127.51,"p99":1461.22,"mean":803.37}},"sourceRun":"Test 08","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","scenarioId":"sharegpt-replay","achievedRps":0.257,"sourceStatus":"complete","sourceTestId":"08-sharegpt","configuredRps":0.3,"prefixCaching":false,"totalRequests":250,"successfulRequests":250,"totalTokenThroughput":120.6,"peakConcurrentRequests":26},{"id":"muse-glimmer-30b-bf16-reasoning","date":"2026-08-12","metrics":{"e2eMs":{"p50":1714680.97,"p90":2445566.89,"p95":2603616.32,"p99":2663653.32,"mean":1700662.34},"tpotMs":{"p50":432.34,"p90":477.96,"p95":484.73,"p99":494.31,"mean":422.32},"ttftMs":{"p50":1507.45,"p90":2237.62,"p95":2803.67,"p99":2994.32,"mean":1562.78}},"sourceRun":"Test 09","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","scenarioId":"reasoning","achievedRps":0.018,"sourceStatus":"complete","sourceTestId":"09-reasoning","configuredRps":0.2,"prefixCaching":false,"totalRequests":50,"successfulRequests":50,"totalTokenThroughput":95.77,"peakConcurrentRequests":50},{"id":"muse-glimmer-30b-bf16-monday-peak-random-4k","date":"2026-08-12","metrics":{"e2eMs":{"p50":208726.83,"p90":376081.32,"p95":391684.47,"p99":419990.49,"mean":213915.68},"tpotMs":{"p50":419.22,"p90":453.07,"p95":484.78,"p99":576.57,"mean":420.9},"ttftMs":{"p50":3842.02,"p90":6727.62,"p95":23125.37,"p99":53593.73,"mean":6074.99}},"sourceRun":"Test 10","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","scenarioId":"monday-peak-random-4k","achievedRps":0.112,"sourceStatus":"complete","sourceTestId":"10-monday-peak","configuredRps":1.5,"prefixCaching":false,"totalRequests":300,"successfulRequests":300,"totalTokenThroughput":511.52,"peakConcurrentRequests":28}],"rateSweep":{"date":"2026-08-12","capacity":{"slo2000":null,"slo5000":null,"slo10000":null},"sourceRun":"Test 11","sourceUrl":"https://github.com/djangodevreng/dgx-spark-benchmarks/tree/a948cec23b054c62fef595bad3cdb284066922ac/results/muse-glimmer/muse-glimmer-30b/bf16/","abortedAtRps":null,"queueKneeRps":null,"sourceStatus":"complete","sourceTestId":"11-rate-sweep","totalRequests":850,"successfulRequests":850}}