FitMyLLM
▸ NVIDIA· MAXWELL 2.0

NVIDIA Quadro M6000 24 GB

Running LLMs on the Quadro M6000 24 GB — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
24 GB
HIGH-END
BANDWIDTH
317.4
GB/S
MODELS Q4
293/449
65%
7B Q4 SPEED
~36
FAST
▸ MODEL COVERAGE @ Q465% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~85
TOK/S
7B
~36
TOK/S
14B
~18
TOK/S
32B
~8
TOK/S
70B
—
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS →
▸ SPECIFICATIONS
VRAM
24 GB
BANDWIDTH
317.4 GB/s
FP16 COMPUTE
6.8 TFLOPS
TDP
250W
MEMORY
GDDR5
ARCHITECTURE
Maxwell 2.0
CUDA CORES
3,072
PCIE
Gen 3 x16
216
FAST MODELS · >30 TOK/S
Real-time chat speed
283
USABLE · >10 TOK/S
Comfortable for all tasks
293
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Quadro M6000 24 GB (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on Vast.ai →Or RunPod →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 293
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
2821
TOK/S · 2% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1881
TOK/S · 2% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
1814
TOK/S · 2% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
1814
TOK/S · 2% VRAM
›
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
992
TOK/S · 3% VRAM
›
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
940
TOK/S · 3% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
833
TOK/S · 3% VRAM
›
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
758
TOK/S · 3% VRAM
›
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
758
TOK/S · 3% VRAM
›
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
758
TOK/S · 3% VRAM
›
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
725
TOK/S · 3% VRAM
›
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
705
TOK/S · 3% VRAM
›
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
668
TOK/S · 3% VRAM
›
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
508
TOK/S · 3% VRAM
›
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
508
TOK/S · 3% VRAM
›
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
488
TOK/S · 3% VRAM
›
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
447
TOK/S · 3% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
447
TOK/S · 3% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
423
TOK/S · 4% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
423
TOK/S · 4% VRAM
›
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
423
TOK/S · 4% VRAM
›
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
410
TOK/S · 4% VRAM
›
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
343
TOK/S · 4% VRAM
›
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
339
TOK/S · 4% VRAM
›
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
313
TOK/S · 4% VRAM
›
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
292
TOK/S · 4% VRAM
›
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
270
TOK/S · 4% VRAM
›
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
235
TOK/S · 5% VRAM
›
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
231
TOK/S · 5% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
212
TOK/S · 5% VRAM
›
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
212
TOK/S · 5% VRAM
›
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
212
TOK/S · 5% VRAM
›
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
212
TOK/S · 5% VRAM
›
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
195
TOK/S · 5% VRAM
›
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
195
TOK/S · 5% VRAM
›
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
195
TOK/S · 5% VRAM
›
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
188
TOK/S · 5% VRAM
›
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
179
TOK/S · 6% VRAM
›
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
179
TOK/S · 6% VRAM
›
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
169
TOK/S · 23% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Quadro M6000 24 GB.

▸Find models for Quadro M6000 24 GBCompare with other GPUs
WHAT THIS CARD IS WORTH

Quadro M6000 24 GB holds 293 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is DeepSeek Coder 33B at IQ4_XS.

TOKENS/SEC PER $100
—
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
—
what memory costs on this card
THE BIGGEST IT TAKES
DeepSeek Coder 33B33B · IQ4_XS21.6 GB9 tok/sEST
DeepSeek-R1-Distill-Qwen-32B32.8B · IQ4_XS21.5 GB9 tok/sEST
Qwen3 32B32.8B · IQ4_XS21.5 GB9 tok/sEST
Qwen2.5-32B32.5B · IQ4_XS21.3 GB9 tok/sEST
Qwen 2.5 Coder 32B32.5B · IQ4_XS21.3 GB9 tok/sEST
QwQ-32B32.5B · IQ4_XS21.3 GB9 tok/sEST
Granite Switch 4.1 30B Preview32.24B · IQ4_XS21.1 GB10 tok/sEST
OLMo-2-0325-32B32.2B · IQ4_XS21.1 GB10 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M3 Max (36GB)27 GB$2,4991.5 tok/s per $100
M3 Pro (36GB)27 GB$1,9991.2 tok/s per $100
RTX 509032 GB$1,9997.9 tok/s per $100
RTX 5090 D32 GB$1,9997.9 tok/s per $100
Quadro M6000 24 GB24 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

NVIDIA Quadro M6000 24 GB — 24 GB VRAM.

▸ QUADRO M6000 24 GB SPEC
BRAND
NVIDIA
VRAM
24 GB GDDR5
BANDWIDTH
317.4 GB/s
FP16 COMPUTE
6.8 TFLOPS
FP32 COMPUTE
6.8 TFLOPS
CUDA CORES
3,072
TDP
250 W
ARCHITECTURE
Maxwell 2.0
▸ AI CAPABILITY
293/ 449 models @ Q4

With 24 GB VRAM and 317.4 GB/s bandwidth, this GPU handles models up to 30.5B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~36 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR QUADRO M6000 24 GB
293 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Qwen3 30B A3B30.5B19.1 GB8546.7
Qwen3-Coder 30B-A3B30.5B19.1 GB7736.9
Qwen3-30B-A3B Instruct 250730.5B19.1 GB7743.0
MPT-30B30B18.8 GB826.8
OPT 30B30B18.8 GB86.3
Qwen3-Omni 30B-A3B30B18.8 GB8540.6
Granite 4.1 30B30B18.8 GB824.7
TranslateGemma 27B28.84B18.1 GB938.6
PaliGemma 2 28B28B17.6 GB938.6
ERNIE 4.5 VL 28B A3B Thinking28B17.6 GB85—
Qwen3.5-27B27.8B17.5 GB959.4
Qwen 3.8 27B27.78B17.5 GB964.6
gemma-3-27b27.4B17.2 GB927.2
gemma-2-27b27.2B17.1 GB934.6
Qwen 3.6 27B27B17.0 GB941.1
Gemma 4 26B A4B26B16.4 GB6347.9
Aria 25B A3.9B25.3B16.0 GB6564.8
Mistral-Small-24B24B15.2 GB1125.0
Mistral-Small-3.1-24B24B15.2 GB1128.8
Magistral Small 24B24B15.2 GB1147.0