InternLM
InternLM 20B
Legacy
1.1KDescargas94Me gustaJul 2024Publicado8K tokensContextoInternLMLicencia22 EntradaCalidad
InternLM 20B (20B parameters) requires approximately 34.2 GB of VRAM with Q5_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 40 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run InternLM 20B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "internlm/internlm2_5-20b-chat" \
--hf-file "internlm2_5-20b-chat-Q5_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Parameters20B
Architecturedense
Context8K tokens
Modalitytext
Min RAM7.8 GB
Rec. RAM14.4 GB (Q5_K_M)
LicenseInternLM
FamilyInternLM
✓ Code✓ Chat
About this model
- •Outstanding reasoning capability: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-27B
- •Stronger tool use: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation has be released in...
Modelos relacionados
Selecciones rápidas
Mejor hardware
Mejores opciones para InternLM 20B
Ejecutar este modelo
Opciones de cuantización
Estimaciones de VRAM por nivel de cuantización
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | — |
Q3_K_S | 3 | 9.8 GB | Low | — |
NVFP4 | 4 | 11.2 GB | Medium | — |
Q4_K_M | 4 | 12.2 GB | Medium | — |
Q5_K_M | 5 | 14.4 GB | High | — |
Q6_K | 6 | 16.4 GB | High | — |
Q8_0 | 8 | 21.4 GB | Very High | — |
F16 | 16 | 41.0 GB | Maximum | — |
Quality benchmarks
InternLM 20B benchmark scores
Reasoning
MMLU-Pro33.3%
GPQA Diamond9.5%
MATH-50040.8%
ARC Challenge—
General
Chatbot Arena—
IFEval70.1%
Source: community · 2025-01-01
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Weights14.4 GB
KV Cache18.3 GB
Runtime0.9 GB
Headroom0.6 GB
Preguntas frecuentes
FAQ — InternLM 20B
Ver también