muse-glimmer 30B

121 records across 13 hardware.

hardware	model	quant	backend	tok/s	pp tok/s	W	ttft s	ctx/tg	date	class	flags	source
Radeon 8060S	muse-glimmer 30B 30B	Q4_K	llama.cpp (ROCm)	80	–	–	–	–	2026-08	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	78.9	233.9	–	–	4096	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	78.9	233.9	–	–	4096	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	77.5	233.9	–	–	4096	2026-10-14	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	55.3	196.8	–	–	1024	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	54.9	196.1	–	–	1024	2026-10-14	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	53.9	198.9	–	–	1024	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	53.9	198.9	–	–	1024	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	49.3	192.6	–	–	1024	2026-10-15	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	49.3	192.6	–	–	1024	2026-10-15	community	contradiction	source
M5 Max	muse-glimmer 30B	6bit	oMLX	40.2	663.8	–	–	4096	2026-10-08	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	38.8	236.5	–	–	8192	2026-10-14	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	37.9	236.7	–	–	8192	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	37.9	236.7	–	–	8192	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	37.6	237.1	–	–	8192	2026-10-15	community	–	source
M5 Max	muse-glimmer 30B	6bit	oMLX	37.1	367.2	–	–	1024	2026-10-08	community	–	source
Radeon 8060S	muse-glimmer 30B 30B	Q4_K	llama.cpp (ROCm)	37	–	–	–	–	2026-08	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	35.3	236.5	–	–	8192	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	35.3	236.5	–	–	8192	2026-10-15	community	–	source
M5 Max	muse-glimmer 30B	oQ4e	oMLX	32.6	824.1	–	–	1024	2026-10-15	community	–	source
M5 Max	muse-glimmer 30B	oQ4e	oMLX	32.3	800.3	–	–	4096	2026-10-15	community	–	source
M5 Max	muse-glimmer 30B	oQ4e	oMLX	31.9	717.7	–	–	8192	2026-10-15	community	–	source
M5 Max	muse-glimmer 30B	oQ4e	oMLX	30.7	693.3	–	–	16384	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	30.1	231.9	–	–	16384	2026-10-14	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	29.4	229.7	–	–	16384	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	29.4	229.7	–	–	16384	2026-10-15	community	–	source
M5 Max	muse-glimmer 30B	oQ4e	oMLX	29.1	661.9	–	–	32768	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	28.4	259.1	–	–	1024	2026-10-15	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	28.4	259.2	–	–	1024	2026-10-15	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	28.2	255.4	–	–	1024	2026-10-15	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	27.7	252.8	–	–	8192	2026-10-15	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	27.6	252.8	–	–	8192	2026-10-15	community	contradiction	source
M5 Max	muse-glimmer 30B 30B	Q4_K_M	MLX	27	–	–	0.4	–	2026-08	sourced	–	source
M5 Max	muse-glimmer 30B	oQ4e	oMLX	27.0	808.9	–	–	131072	2026-10-18	community	–	source
M1 Ultra	muse-glimmer 30B	mxfp4	oMLX	26.6	202.6	–	–	4096	2026-10-13	community	–	source
M5 Max	muse-glimmer 30B	4bit	oMLX	26.5	969.2	–	–	4096	2026-10-13	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	26.1	220.1	–	–	4096	2026-10-15	community	contradiction outlier	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	24.5	227.3	–	–	65536	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	24.5	227.3	–	–	65536	2026-10-15	community	–	source
Arc Pro B60	muse-glimmer 30B	Q4_K - Medium	llama.cpp	24.34	686.91	–	–	tg128	2026-08-29	community	–	source
Arc Pro B60	muse-glimmer 30B	Q4_K - Medium	llama.cpp	24.33	206.45	–	–	tg128	2026-08-29	community	–	source
M4 Max	muse-glimmer 30B 30B	Q4_K_M	MLX	24	–	–	0.5	–	2026-08	sourced	–	source
M5 Max	muse-glimmer 30B	4bit	oMLX	24.0	872.3	–	–	65536	2026-10-11	community	–	source
Arc Pro B60	muse-glimmer 30B	Q4_K - Medium	llama.cpp	23.94	649.88	–	–	tg128	2026-08-29	community	–	source
Arc Pro B60	muse-glimmer 30B	Q4_K - Medium	llama.cpp	23.92	202.45	–	–	tg128	2026-08-29	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	23.2	254.2	–	–	1024	2026-10-08	community	–	source
M5 Max	muse-glimmer 30B	6bit	oMLX	22.5	877.7	–	–	4096	2026-10-12	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	22.5	205.0	–	–	1024	2026-10-17	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	22.4	204.6	–	–	1024	2026-10-17	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	22.3	207.6	–	–	1024	2026-10-17	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	22.2	201.3	–	–	8192	2026-10-08	community	–	source
M5 Max	muse-glimmer 30B	4bit	oMLX	22.2	785.3	–	–	131072	2026-10-11	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	22.0	215.9	–	–	65536	2026-10-15	community	contradiction	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	22.0	215.9	–	–	65536	2026-10-15	community	contradiction	source
M5 Max	muse-glimmer 30B	6bit	oMLX	21.9	785.8	–	–	16384	2026-10-12	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	21.6	215.8	–	–	4096	2026-10-08	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	21.5	184.8	–	–	4096	2026-10-17	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	21.4	185.0	–	–	4096	2026-10-17	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	21.2	200.8	–	–	16384	2026-10-08	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	21.1	180.2	–	–	4096	2026-10-17	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.8	194.4	–	–	1024	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.8	194.4	–	–	1024	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.4	189.2	–	–	4096	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.4	189.2	–	–	4096	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.3	184.5	–	–	16384	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.3	184.5	–	–	16384	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.2	171.0	–	–	8192	2026-10-15	community	–	source
M2 Max	muse-glimmer 30B	oQ4e	oMLX	20.2	171.0	–	–	8192	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	oQ4e	oMLX	20.0	216.3	–	–	65536	2026-10-15	community	contradiction	source
M5 Max	muse-glimmer 30B	6bit	oMLX	19.7	766.5	–	–	131072	2026-10-10	community	–	source
M5 Max	muse-glimmer 30B	6bit	oMLX	19.5	762.5	–	–	131072	2026-10-10	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	19.1	188.5	–	–	32768	2026-10-08	community	–	source
M5 Max	muse-glimmer 30B	6bit	oMLX	19.1	632.7	–	–	131072	2026-10-12	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	18.68	544.62	–	–	tg128	2026-08-17	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	18.68	546.94	–	–	tg128	2026-08-17	community	–	source
M1 Max	muse-glimmer 30B	oQ4e	oMLX	18.4	109.8	–	–	1024	2026-10-14	community	–	source
M5 Max	muse-glimmer 30B	6bit	oMLX	18.2	693.8	–	–	199680	2026-10-10	community	–	source
M5 Max	muse-glimmer 30B	6bit	oMLX	18.1	692.3	–	–	199680	2026-10-10	community	–	source
M1 Max	muse-glimmer 30B	oQ4e	oMLX	18.0	105.0	–	–	4096	2026-10-14	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	17.9	625.05	–	–	tg128	2026-08-17	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.9	480.4	–	–	1024	2026-10-15	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	17.88	623.17	–	–	tg128	2026-08-17	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.8	500.4	–	–	4096	2026-10-15	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.6	470.9	–	–	1024	2026-10-15	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.5	481.3	–	–	4096	2026-10-13	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.5	471.2	–	–	4096	2026-10-15	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.3	495.0	–	–	8192	2026-10-15	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	17.2	170.3	–	–	65536	2026-10-08	community	–	source
M5 Pro	muse-glimmer 30B	oQ4e	oMLX	17.1	487.5	–	–	16384	2026-10-13	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	15.4	130.2	–	–	1024	2026-10-16	community	–	source
M4 Max	muse-glimmer 30B	4bit	oMLX	15.2	150.5	–	–	131072	2026-10-08	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	15.0	128.0	–	–	4096	2026-10-16	community	–	source
M5 Pro	muse-glimmer 30B	4bit	oMLX	14.8	395.1	–	–	1024	2026-10-15	community	–	source
M5 Pro	muse-glimmer 30B	4bit	oMLX	14.8	395.1	–	–	1024	2026-10-15	community	–	source
M5 Pro	muse-glimmer 30B	4bit	oMLX	14.6	409.3	–	–	4096	2026-10-15	community	–	source
M5 Pro	muse-glimmer 30B	4bit	oMLX	14.6	409.3	–	–	4096	2026-10-15	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	14.6	121.0	–	–	8192	2026-10-16	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	14.3	116.2	–	–	16384	2026-10-16	community	–	source
M1 Max	muse-glimmer 30B	6bit	oMLX	14.2	106.0	–	–	1024	2026-10-13	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	13.7	114.3	–	–	32768	2026-10-16	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	13.66	528.15	–	–	tg128	2026-08-17	community	–	source
M5 Max	muse-glimmer 30B	Q4_K_XL	llama.cpp	13.64	–	–	–	–	2026-09-30	community	–	source
M1 Max	muse-glimmer 30B	6bit	oMLX	13.6	104.8	–	–	4096	2026-10-13	community	–	source
M1 Max	muse-glimmer 30B	6bit	oMLX	13.6	102.9	–	–	8192	2026-10-13	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	13.4	108.9	–	–	65536	2026-10-14	community	–	source
M4 Pro	muse-glimmer 30B	oQ4e	oMLX	13.0	105.8	–	–	65536	2026-10-16	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	12.57	598.6	–	–	tg128	2026-08-17	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	10.12	580.37	–	–	tg128	2026-08-17	community	–	source
M4 Pro	muse-glimmer 30B 30B	Q4_K_M	LM Studio	10	–	–	0.8	–	2026-08	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	9.98	467.16	–	–	tg128	2026-08-17	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	9.82	547.77	–	–	tg128	2026-08-17	community	contradiction	source
M5 Max	muse-glimmer 30B	Q4_K_XL	llama.cpp	9.24	–	–	–	–	2026-09-30	community	–	source
M6	muse-glimmer 30B 30B	unstated	LM Studio	9	–	–	–	–	2026-10	community	–	source
Arc A770	muse-glimmer 30B	Q4_K - Small	llama.cpp (SYCL)	8.69	445.85	–	–	tg128	2026-08-17	community	–	source
M5	muse-glimmer 30B	mxfp4	oMLX	8.6	185.4	–	–	1024	2026-10-15	community	–	source
M5	muse-glimmer 30B	oQ4e	oMLX	7.9	204.7	–	–	1024	2026-10-15	community	–	source
M5	muse-glimmer 30B	nvfp4	oMLX	7.8	195.8	–	–	1024	2026-10-15	community	–	source
AMD Custom GPU 0932	muse-glimmer 30B 27.85B	Q4_K - Medium	llama.cpp (Vulkan)	3.83	19.77	–	–	tg128	2026-08-20	community	–	source
AMD Custom GPU 0932	muse-glimmer 30B 27.85B	Q4_K - Medium	llama.cpp (Vulkan)	3.77	19.63	–	–	tg128	2026-08-20	community	–	source
M5 Max	muse-glimmer 30B	Q4_K_XL	llama.cpp	–	26.98	–	–	–	2026-09-30	community	–	source
M5 Max	muse-glimmer 30B	Q4_K_XL	llama.cpp	–	58.76	–	–	–	2026-09-30	community	–	source

← all models